diff --git a/prototypes/fine_tuning_spaCy/__pycache__/training_data.cpython-311.pyc b/prototypes/fine_tuning_spaCy/__pycache__/training_data.cpython-311.pyc
index 3cd4fc0..c70e2f9 100644
Binary files a/prototypes/fine_tuning_spaCy/__pycache__/training_data.cpython-311.pyc and b/prototypes/fine_tuning_spaCy/__pycache__/training_data.cpython-311.pyc differ
diff --git a/prototypes/fine_tuning_spaCy/data/train.spacy b/prototypes/fine_tuning_spaCy/data/train.spacy
index 17fd534..7d9dfbb 100644
Binary files a/prototypes/fine_tuning_spaCy/data/train.spacy and b/prototypes/fine_tuning_spaCy/data/train.spacy differ
diff --git a/prototypes/fine_tuning_spaCy/entities_output.json b/prototypes/fine_tuning_spaCy/entities_output.json
index 4e58e7f..6d98983 100644
--- a/prototypes/fine_tuning_spaCy/entities_output.json
+++ b/prototypes/fine_tuning_spaCy/entities_output.json
@@ -1,24 +1,4 @@
 [
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Content",
-    "page": 2
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Case & Views",
-    "page": 2
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 2
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 3
-  },
   {
     "label": "RISIKOPROFIL",
     "entity": "Core and Core+",
@@ -26,114 +6,14 @@
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 5
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "CITIES \n-",
-    "page": 6
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "UK,",
-    "page": 6
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Czech Republic,",
-    "page": 6
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "COMPLETE",
-    "page": 6
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "closed-end and",
-    "page": 6
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Club Deals",
-    "page": 6
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Ventures;",
-    "page": 6
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 6
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Office",
-    "page": 6
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "lndustrial/logistics",
-    "page": 6
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Comprehensive service",
+    "entity": "core, core+, value-added",
     "page": 7
   },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Club Deals",
-    "page": 7
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Club Deals: investing with similar-minded",
-    "page": 7
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 7
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "core, core+",
-    "page": 7
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "86",
-    "page": 8
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "100",
-    "page": 8
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 8
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 9
-  },
   {
     "label": "RISIKOPROFIL",
     "entity": "Core/Core+",
     "page": 10
   },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Cities",
-    "page": 10
-  },
   {
     "label": "RISIKOPROFIL",
     "entity": "core/core+",
@@ -146,122 +26,27 @@
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Europe",
+    "entity": "UK, DE, BE, NL, LU,",
     "page": 10
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "40%",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "UK,",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "NL,",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "LU,",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Nordics,",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "IT,",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "25% in",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core: max",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Concentration limits:",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Cash: 4",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 10
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "(€1 Bn of",
-    "page": 11
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "AIF",
-    "page": 11
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Form:",
-    "page": 11
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Currency: EUR",
-    "page": 11
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "(Dec",
-    "page": 11
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Management/ Fund",
-    "page": 11
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "+ M€). Fee",
-    "page": 11
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "IRR (payable by investors",
-    "page": 11
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 11
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core / Core",
+    "entity": "Core / Core +",
     "page": 12
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "core \n/ core+",
+    "entity": "core\n/ core+",
     "page": 12
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "core \n/ core+",
+    "entity": "core",
+    "page": 12
+  },
+  {
+    "label": "RISIKOPROFIL",
+    "entity": "Term / core+",
     "page": 12
   },
   {
@@ -271,274 +56,34 @@
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "8,9",
+    "entity": "6,4 6,4",
     "page": 13
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "8,2",
-    "page": 13
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Comments",
-    "page": 13
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "PEPFI: Pan",
-    "page": 13
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 13
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "2019",
+    "entity": "Country /",
     "page": 14
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Country / city",
+    "entity": "Core\nCore\nCore\nCore\nCore\nCore\nCore\nCore",
     "page": 14
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Comments",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Offices",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n80m",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Commission - well",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n40m",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "District -",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "100",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Completely",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n<50m \nGood",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n400m \nGood",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n300m",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n99m-102m",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Leopold / Location",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "1992 / WAL",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n85m-90m",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n50m-55m",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "2020",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 14
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "2019",
+    "entity": "Country /",
     "page": 15
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Country / city",
+    "entity": "Core\nCore\nCore\nCore\nCore\nCore",
     "page": 15
   },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Brussels",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Denis",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n34-",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n44m-46m \nOffices",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n100-150m",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Offices",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n90-",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Offices",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \n150 -170",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Location",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "CBD",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Tenancy",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "2020 -",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "centre,",
-    "page": 15
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "19",
-    "page": 16
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 16
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Committee",
-    "page": 17
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "2.3bn)",
-    "page": 17
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "6.0 Bn*",
-    "page": 17
-  },
   {
     "label": "RISIKOPROFIL",
     "entity": "countries, giving",
     "page": 18
   },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Country",
-    "page": 18
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Leasing",
-    "page": 18
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 18
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 19
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Coordination with property",
-    "page": 19
-  },
   {
     "label": "RISIKOPROFIL",
     "entity": "core/core+",
@@ -551,612 +96,72 @@
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Source :",
-    "page": 20
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "COP",
+    "entity": "D, and",
     "page": 21
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "21",
-    "page": 21
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Committee",
-    "page": 22
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Research,",
-    "page": 22
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Controlling, Liability",
-    "page": 22
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Conducting",
-    "page": 22
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Officer,",
-    "page": 22
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Officer",
-    "page": 22
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Views",
-    "page": 23
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 23
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Market",
-    "page": 24
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Views",
-    "page": 24
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "S1 2010 -",
-    "page": 24
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "2019",
-    "page": 24
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Market",
-    "page": 25
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Views",
-    "page": 25
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "V",
-    "page": 25
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "S1",
-    "page": 25
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "2010-",
-    "page": 25
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "2019",
-    "page": 25
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 25
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Vienne",
-    "page": 25
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Prague",
-    "page": 25
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Milan",
-    "page": 25
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Market",
+    "entity": "UK, DE, BE, NL, LU,",
     "page": 26
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Views",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Conviction - Strong",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Conviction - Medium",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Conviction - Low",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Hospitality",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Hotels,",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "UK,",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "NL,",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "LU,",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Nordics,",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "SP,",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "IT,",
-    "page": 26
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Current views accross",
+    "entity": "core or",
     "page": 27
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Conviction -",
+    "entity": "Core +",
     "page": 27
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Conviction - Medium",
-    "page": 27
+    "entity": "kgCO,e",
+    "page": 30
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Conviction - Low",
-    "page": 27
+    "entity": "C,",
+    "page": 32
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "core can m",
-    "page": 27
+    "entity": "KfW, Dwp",
+    "page": 35
+  },
+  {
+    "label": "RISIKOPROFIL",
+    "entity": "Bank,",
+    "page": 35
   },
   {
     "label": "RISIKOPROFIL",
     "entity": "Core",
-    "page": 27
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "core strategies could",
-    "page": 27
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core Offices, quality Retail asset",
-    "page": 27
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Czech Rep",
-    "page": 27
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Views",
-    "page": 27
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Information /",
-    "page": 28
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 28
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "71/ 100",
-    "page": 29
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "C",
-    "page": 29
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "86",
-    "page": 29
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Carbone",
-    "page": 30
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "(%",
-    "page": 30
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "35",
-    "page": 30
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "C) Exposure",
-    "page": 31
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "canicules,",
-    "page": 31
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Canicules",
-    "page": 31
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "ESG",
-    "page": 32
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 32
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "calculation,",
-    "page": 33
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "1/5",
-    "page": 34
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \nClosed in 2018",
-    "page": 34
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Portico",
-    "page": 34
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \nClosed in 2018",
-    "page": 34
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Value:",
-    "page": 34
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "CoC:",
-    "page": 34
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "CoC:",
-    "page": 34
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Nedeland",
-    "page": 34
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Comments",
-    "page": 34
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "2/5",
-    "page": 35
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Comments",
-    "page": 35
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \nParking 64",
-    "page": 35
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Value:",
-    "page": 35
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "CoC:",
-    "page": 35
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Commercial 1,028 sqm",
-    "page": 35
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \nParking 347",
-    "page": 35
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Value:",
-    "page": 35
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "141 ,2m",
-    "page": 35
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 35
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "3/5",
     "page": 36
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Deal",
+    "entity": "Core",
     "page": 36
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Central",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \nClosed in",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \nClosed in",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Value:",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "m2 \nStorage 1,636",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "m2",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "100%",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "IRR 1 DY:",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "(years):",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Cash-on-cash:",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "IRR 1 DY:",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "(occupancy 96%",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "net",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Comments",
-    "page": 36
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "4/5",
+    "entity": "Core",
     "page": 37
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Comments",
+    "entity": "Core",
     "page": 37
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "Defense",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "182,765 m2",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Defense",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "RTE,",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \nWALB (years):",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "1 ,",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "IRR 10Y",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Hekla",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Defense",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \nWALB (years):",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "IRR 10Y",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
-    "page": 37
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "5/5",
+    "entity": "Core",
     "page": 38
   },
   {
     "label": "RISIKOPROFIL",
-    "entity": "m2",
-    "page": 38
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \nTenants:",
-    "page": 38
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "(occupancy 68",
-    "page": 38
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "IRR 10Y",
-    "page": 38
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "m2",
-    "page": 38
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Core \nTenants:",
-    "page": 38
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "(occupancy 98.4%",
-    "page": 38
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "9.7",
-    "page": 38
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "IRR 10Y",
-    "page": 38
-  },
-  {
-    "label": "RISIKOPROFIL",
-    "entity": "Europe",
+    "entity": "Core",
     "page": 38
   }
 ]
\ No newline at end of file
diff --git a/prototypes/fine_tuning_spaCy/output/model-best/meta.json b/prototypes/fine_tuning_spaCy/output/model-best/meta.json
index ca58b77..daabc76 100644
--- a/prototypes/fine_tuning_spaCy/output/model-best/meta.json
+++ b/prototypes/fine_tuning_spaCy/output/model-best/meta.json
@@ -46,7 +46,7 @@
         "f":1.0
       }
     },
-    "tok2vec_loss":0.000000011,
-    "ner_loss":0.0000000457
+    "tok2vec_loss":0.000000029,
+    "ner_loss":0.0000000614
   }
 }
\ No newline at end of file
diff --git a/prototypes/fine_tuning_spaCy/output/model-best/ner/model b/prototypes/fine_tuning_spaCy/output/model-best/ner/model
index 4909428..8a0c5ae 100644
Binary files a/prototypes/fine_tuning_spaCy/output/model-best/ner/model and b/prototypes/fine_tuning_spaCy/output/model-best/ner/model differ
diff --git a/prototypes/fine_tuning_spaCy/output/model-best/ner/moves b/prototypes/fine_tuning_spaCy/output/model-best/ner/moves
index e27560d..e72ba15 100644
--- a/prototypes/fine_tuning_spaCy/output/model-best/ner/moves
+++ b/prototypes/fine_tuning_spaCy/output/model-best/ner/moves
@@ -1 +1 @@
-��moves�x{"0":{},"1":{"RISIKOPROFIL":20},"2":{"RISIKOPROFIL":20},"3":{"RISIKOPROFIL":20},"4":{"RISIKOPROFIL":20,"":1},"5":{"":1}}�cfg��neg_key�
\ No newline at end of file
+��moves�x{"0":{},"1":{"RISIKOPROFIL":45},"2":{"RISIKOPROFIL":45},"3":{"RISIKOPROFIL":45},"4":{"RISIKOPROFIL":45,"":1},"5":{"":1}}�cfg��neg_key�
\ No newline at end of file
diff --git a/prototypes/fine_tuning_spaCy/output/model-best/tok2vec/model b/prototypes/fine_tuning_spaCy/output/model-best/tok2vec/model
index 0bf1b64..1cfa6a5 100644
Binary files a/prototypes/fine_tuning_spaCy/output/model-best/tok2vec/model and b/prototypes/fine_tuning_spaCy/output/model-best/tok2vec/model differ
diff --git a/prototypes/fine_tuning_spaCy/output/model-best/vocab/strings.json b/prototypes/fine_tuning_spaCy/output/model-best/vocab/strings.json
index 4293997..7569f1d 100644
--- a/prototypes/fine_tuning_spaCy/output/model-best/vocab/strings.json
+++ b/prototypes/fine_tuning_spaCy/output/model-best/vocab/strings.json
@@ -4,6 +4,8 @@
   " ",
   "  ",
   "\"",
+  "$",
+  "%",
   "'",
   "''",
   "'-(",
@@ -46,6 +48,8 @@
   ")/\u00af",
   "):",
   "*",
+  "+",
+  ",",
   "-",
   "-((",
   "-))",
@@ -100,16 +104,40 @@
   ".\u00e4.",
   "/",
   "/3",
+  "/Core+",
+  "/Xxxx+",
+  "/core+",
   "/d",
+  "/xxxx+",
   "0",
+  "0%+",
   "0.0",
   "0.o",
+  "022",
+  "032",
+  "034",
   "0_0",
   "0_o",
   "1",
+  "1.",
+  "10",
+  "12",
+  "2",
+  "2.",
+  "20",
+  "2022",
+  "2032",
+  "2034",
+  "250",
   "3",
+  "3.",
   "33",
   "333",
+  "35",
+  "5",
+  "50",
+  "7",
+  "7,50%+",
   "8",
   "8)",
   "8-",
@@ -234,9 +262,20 @@
   "Abt.",
   "Abteilung",
   "Add",
+  "Aktueller",
+  "Allgemeine",
+  "Amsterdam",
+  "Anlagestrategien",
+  "Anlagevehikels",
+  "Ansprechpartners",
+  "Antagevehikels",
   "Apr",
   "Apr.",
   "April",
+  "Art",
+  "Assets",
+  "Aufl\u00f6sung",
+  "Aufwertung",
   "Aug",
   "Aug.",
   "August",
@@ -250,6 +289,8 @@
   "Bd",
   "Bd.",
   "Beispiel",
+  "Berlin",
+  "Bestandsentwicklungen",
   "Betr",
   "Betr.",
   "Betreff",
@@ -271,6 +312,8 @@
   "Chr.",
   "Cie",
   "Cie.",
+  "Cities",
+  "Closings",
   "Co",
   "Co.",
   "Core",
@@ -279,12 +322,15 @@
   "D",
   "D.",
   "D.C.",
+  "Deutschland",
+  "Deutschlands",
   "Dez",
   "Dez.",
   "Dezember",
   "Di",
   "Di.",
   "Dienstag",
+  "Different",
   "Dipl",
   "Dipl.",
   "Dipl.-Ing",
@@ -294,9 +340,14 @@
   "Donnerstag",
   "Dr",
   "Dr.",
+  "D\u00e4nemark",
   "E",
+  "E-Mail",
   "E.",
+  "Einw",
+  "Europe",
   "European",
+  "Exit",
   "F",
   "F.",
   "FIL",
@@ -310,20 +361,28 @@
   "Februar",
   "Firma",
   "Fond",
+  "Fonds",
   "Fr",
   "Fr.",
+  "Frankreich",
   "Frau",
   "Frl",
   "Frl.",
   "Fr\u00e4ulein",
+  "Fu\u0308hrende",
   "G",
   "G.",
   "G.m.b",
   "G.m.b.H.",
+  "Gateway",
   "Gebr",
   "Gebr.",
+  "Geplantes",
+  "Gesamtrendite",
   "H",
   "H.",
+  "Halten",
+  "Halten-Strategie",
   "Hauptbahnhof",
   "Hbf",
   "Hbf.",
@@ -343,13 +402,21 @@
   "II.",
   "III",
   "III.",
+  "INREV",
+  "IRR",
   "IV",
   "IV.",
+  "Immobilien",
+  "Immobilien-Spezialfonds",
   "Inc",
   "Inc.",
+  "Informationen",
   "Ing",
   "Ing.",
+  "Investmentmanagers",
   "J",
+  "Jahr",
+  "Jahre",
   "Jahrhundert",
   "Jan",
   "Jan.",
@@ -369,16 +436,26 @@
   "K",
   "K.",
   "K.O.",
+  "Kaufen",
+  "Key",
   "L",
   "L'",
   "L.A.",
+  "LTV",
+  "LTY",
+  "Laufzeit",
+  "London",
+  "L\u00e4nderallokation",
   "L\u2019",
   "M",
   "M.",
   "M.A.",
   "M.Sc",
   "M.Sc.",
+  "Manager",
+  "Maximaler",
   "Mehrwertsteuer",
+  "Metropolregionen",
   "Mi",
   "Mi.",
   "Milliarde",
@@ -403,6 +480,9 @@
   "N",
   "N.Y.",
   "N.Y.C.",
+  "Nachvermietungsstrategie",
+  "Name",
+  "Niederlande",
   "Nov",
   "Nov.",
   "November",
@@ -416,14 +496,18 @@
   "O.o",
   "O_O",
   "O_o",
+  "Offen",
+  "Offener",
   "Okt",
   "Okt.",
   "Oktober",
+  "OpCo",
   "Orig",
   "Orig.",
   "Original",
   "P",
   "P.S.",
+  "Paris",
   "Pkt",
   "Pkt.",
   "Prof",
@@ -434,32 +518,44 @@
   "R.",
   "R.I.P.",
   "RE",
+  "REV",
   "RISIKOPROFIL",
   "ROOT",
+  "Rechtsform",
   "Red",
   "Red.",
   "Redaktion",
+  "Risikoprofil",
+  "Risk",
   "S",
   "S'",
   "Sa",
   "Sa.",
   "Samstag",
   "Sc.",
+  "Schweden",
   "Sep",
   "Sep.",
   "Sept",
   "Sept.",
   "September",
+  "Sitz",
+  "Skandinavien",
   "So",
   "So.",
   "Sonntag",
   "St",
   "St.",
+  "Standortaufwertungsstrategie",
+  "Standorte",
   "Std",
   "Std.",
+  "Stil",
   "Str",
   "Str.",
+  "Strategie",
   "Stra\u00dfe",
+  "Struktur",
   "Stunde",
   "S\u2019",
   "T",
@@ -468,6 +564,7 @@
   "Tel",
   "Tel.",
   "Telefon",
+  "Telefonnummer",
   "The",
   "Tr",
   "Tr.",
@@ -488,8 +585,12 @@
   "Value",
   "Vol",
   "Vol.",
+  "W",
+  "Wertstabile",
+  "Wohnimmobilien",
   "X'",
   "X++",
+  "X-Xxxx",
   "X.",
   "X.X",
   "X.X.",
@@ -518,13 +619,25 @@
   "Xxxx",
   "Xxxx+",
   "Xxxx+/Xxxxx",
+  "Xxxx-XXX",
+  "Xxxx-Xxxxx-XXX",
   "Xxxx.",
   "Xxxx.-Xxx",
   "Xxxx.-Xxx.",
   "Xxxxx",
+  "Xxxxx)/Xxxx",
+  "Xxxxx-Xxxxx",
+  "Xx\u0308xxxx",
   "X\u2019",
   "Z",
   "Z.",
+  "Ziel-LTY",
+  "Ziel-Netto-IRR",
+  "Zielanlagestrategie",
+  "Zielregionfen)/Jand",
+  "Zielsektoren",
+  "Zielvolumen",
+  "Ziirraiaein",
   "Zt",
   "Zt.",
   "[",
@@ -578,21 +691,41 @@
   "add",
   "adv",
   "adv.",
+  "ahr",
+  "ail",
+  "aiming",
+  "aktueller",
   "al",
   "al.",
   "allg",
   "allg.",
   "allgemein",
+  "allgemeine",
   "am.",
+  "ame",
+  "amsterdam",
   "an.",
+  "and",
+  "anlagestrategien",
+  "anlagevehikels",
+  "ansprechpartners",
+  "antagevehikels",
   "apr",
   "apr.",
+  "ark",
+  "art",
+  "asset",
+  "assets",
+  "at",
   "at.",
   "ath",
   "auf",
+  "aufl\u00f6sung",
+  "aufwertung",
   "auf\u2019m",
   "aug",
   "aug.",
+  "ausgew\u00e4hlte",
   "ax.",
   "b",
   "b.",
@@ -604,6 +737,8 @@
   "bd.",
   "beispielsweise",
   "ber",
+  "berlin",
+  "bestandsentwicklungen",
   "betr",
   "betr.",
   "beziehungsweise",
@@ -632,23 +767,29 @@
   "c/o",
   "ca",
   "ca.",
+  "cal",
   "cdu",
   "cdu/csu",
   "ce>",
   "chr",
   "chr.",
+  "cht",
   "cie",
   "cie.",
+  "cities",
   "cl.",
+  "closings",
   "co",
   "co.",
   "core",
   "core+",
   "core+/value",
   "csu",
+  "cts",
   "d",
   "d'",
   "d)",
+  "d,dd%+",
   "d-",
   "d-)",
   "d-X",
@@ -661,30 +802,43 @@
   "dX",
   "d_d",
   "d_x",
+  "dam",
   "dd",
   "ddd",
+  "dddd",
   "de",
+  "ded",
   "dem",
+  "den",
+  "der",
   "dergleichen",
+  "des",
+  "deutschland",
+  "deutschlands",
+  "development",
   "dez",
   "dez.",
   "dgl",
   "dgl.",
   "di",
   "di.",
+  "different",
   "dipl",
   "dipl.",
   "dipl.-ing",
   "dipl.-ing.",
   "do",
   "do.",
+  "don",
   "dr",
   "dr.",
   "du",
   "du\u2019s",
   "dv.",
+  "d\u00e4nemark",
   "d\u2019",
   "e",
+  "e-mail",
   "e.",
   "e.V.",
   "e.d",
@@ -699,6 +853,7 @@
   "ebr",
   "ed.",
   "egr",
+  "egy",
   "ehem",
   "ehem.",
   "eigentlich",
@@ -708,12 +863,17 @@
   "eine",
   "einem",
   "einen",
+  "einw",
+  "eit",
   "el.",
+  "els",
   "em.",
   "en.",
   "engl",
   "engl.",
   "englisch",
+  "enhancing",
+  "ent",
   "entspr",
   "entspr.",
   "ep.",
@@ -724,18 +884,23 @@
   "erm.",
   "err",
   "ers",
+  "ersten",
   "er\u2019s",
   "es",
   "etc",
   "etc.",
   "etr",
+  "ets",
+  "europe",
   "european",
   "ev",
   "ev.",
   "eventuell",
   "evtl",
   "evtl.",
+  "exit",
   "expertise",
+  "exposure",
   "ez.",
   "e\u2019s",
   "f",
@@ -746,9 +911,14 @@
   "fam.",
   "feb",
   "feb.",
+  "fen",
+  "festgelegter",
+  "fil",
   "fond",
+  "fonds",
   "fr",
   "fr.",
+  "frankreich",
   "franz\u00f6sisch",
   "frl",
   "frl.",
@@ -756,11 +926,13 @@
   "frz.",
   "fs.",
   "fund",
+  "fu\u0308hrende",
   "f\u2019m",
   "g",
   "g.",
   "g.m.b",
   "g.m.b.h.",
+  "gateway",
   "geb",
   "geb.",
   "gebr",
@@ -772,6 +944,10 @@
   "gegr\u00fcndet",
   "gem",
   "gem.",
+  "gen",
+  "geplantes",
+  "ger",
+  "gesamtrendite",
   "gf.",
   "gfs",
   "ggf",
@@ -780,6 +956,7 @@
   "ggfs.",
   "gg\u00fc",
   "gg\u00fc.",
+  "gie",
   "gl.",
   "good",
   "gr.",
@@ -789,9 +966,12 @@
   "h.",
   "h.c",
   "h.c.",
+  "halten",
+  "halten-strategie",
   "hbf",
   "hbf.",
   "hd.",
+  "hed",
   "hem",
   "hf.",
   "hg",
@@ -799,8 +979,10 @@
   "hil",
   "hinter",
   "hinter\u2019m",
+  "hotels",
   "hr",
   "hr.",
+  "hre",
   "hrn",
   "hrn.",
   "hrsg",
@@ -826,6 +1008,8 @@
   "ich",
   "ich\u2019s",
   "ie.",
+  "ien",
+  "ies",
   "ig.",
   "ihr",
   "ihr\u2019s",
@@ -834,7 +1018,11 @@
   "iii",
   "iii.",
   "il.",
+  "ile",
   "illustration",
+  "ime",
+  "immobilien",
+  "immobilien-spezialfonds",
   "in",
   "in.",
   "inc",
@@ -842,26 +1030,41 @@
   "incl",
   "incl.",
   "ind",
+  "ine",
+  "informationen",
   "ing",
   "ing.",
+  "initiatives",
   "inkl",
   "inkl.",
   "inklusive",
+  "inrev",
   "insb",
   "insb.",
   "insbesondere",
+  "investmentmanagers",
   "investments",
+  "inw",
   "io.",
   "iol",
   "ion",
   "ipl",
+  "irr",
   "is",
   "ise",
+  "isk",
   "iss",
+  "ite",
+  "ith",
+  "ity",
+  "itz",
+  "ium",
   "iv",
   "iv.",
   "j",
   "j.",
+  "jahr",
+  "jahre",
   "jan",
   "jan.",
   "jh",
@@ -882,24 +1085,38 @@
   "kath",
   "kath.",
   "katholisch",
+  "kaufen",
+  "ket",
+  "key",
   "kl.",
   "kt.",
   "l",
   "l'",
   "l.",
   "l.a.",
+  "langfristig",
   "lat",
   "lat.",
+  "laufzeit",
   "laut",
+  "le.g",
+  "ler",
+  "level",
   "lg.",
+  "lin",
   "lio",
   "llg",
   "llt",
   "llv",
+  "london",
   "lt",
   "lt.",
+  "lte",
+  "ltv",
+  "lty",
   "lue",
   "lv.",
+  "l\u00e4nderallokation",
   "l\u2019",
   "m",
   "m.",
@@ -911,19 +1128,30 @@
   "m.m.",
   "m.sc",
   "m.sc.",
+  "mal",
+  "management",
+  "manager",
+  "market",
   "max",
   "max.",
   "maximal",
+  "maximaler",
+  "men",
+  "mer",
+  "metropolregionen",
   "mi",
   "mi.",
+  "million",
   "min",
   "min.",
   "mind",
   "mind.",
   "mindestens",
   "minimal",
+  "minor",
   "mio",
   "mio.",
+  "mit",
   "mo",
   "mo.",
   "monatlich",
@@ -946,18 +1174,26 @@
   "n.r",
   "n.y.",
   "n.y.c.",
+  "nachvermietungsstrategie",
+  "name",
   "nat",
   "nat.",
   "nc.",
   "ncl",
   "nd.",
+  "nde",
+  "nds",
   "ne",
   "nem",
   "nen",
+  "ner",
   "ng.",
   "ngl",
+  "ngs",
+  "niederlande",
   "niv",
   "nkl",
+  "nor",
   "nov",
   "nov.",
   "nr",
@@ -982,23 +1218,32 @@
   "o_o",
   "of",
   "of.",
+  "offen",
+  "offener",
   "og.",
   "okt",
   "okt.",
   "ol.",
   "ond",
   "ood",
+  "opco",
+  "ope",
   "ore",
   "orig",
   "orig.",
   "original",
+  "orm",
   "ov.",
+  "over",
   "p",
   "p.",
   "p.a",
   "p.a.",
   "p.s",
   "p.s.",
+  "pCo",
+  "paris",
+  "pco",
   "pers",
   "pers.",
   "phil",
@@ -1008,26 +1253,35 @@
   "pl.",
   "portfolio",
   "pr.",
+  "premium",
   "prof",
   "prof.",
+  "profile",
+  "projects",
   "pt.",
   "pw.",
   "q",
   "q.",
   "q.e.d",
   "q.e.d.",
+  "quality",
   "r",
   "r.",
   "r.i.p.",
   "rd.",
   "re",
   "re+",
+  "rechtsform",
   "red",
   "red.",
+  "ren",
   "rer",
   "rer.",
+  "rev",
   "rig",
+  "ris",
   "risikoprofil",
+  "risk",
   "rl.",
   "rm.",
   "rn.",
@@ -1035,6 +1289,7 @@
   "rr.",
   "rs.",
   "rsg",
+  "rte",
   "rz.",
   "r\u00f6m",
   "r\u00f6m.",
@@ -1050,6 +1305,7 @@
   "sa",
   "sa.",
   "sb.",
+  "schweden",
   "sd.",
   "sen",
   "sen.",
@@ -1057,10 +1313,13 @@
   "sep.",
   "sept",
   "sept.",
+  "set",
   "sf.",
   "sg.",
   "sie",
   "sie\u2019s",
+  "sitz",
+  "skandinavien",
   "so",
   "so.",
   "sog",
@@ -1072,28 +1331,43 @@
   "ss.",
   "st",
   "st.",
+  "standortaufwertungsstrategie",
+  "standorte",
   "std",
   "std.",
   "stellv",
   "stellv.",
+  "stil",
   "str",
   "str.",
+  "strategie",
+  "strategy",
+  "struktur",
   "sw.",
   "s\u2019",
   "t",
   "t.",
+  "tactical",
   "tc.",
   "td.",
   "tel",
   "tel.",
+  "telefonnummer",
+  "ten",
   "ter",
+  "tes",
   "th.",
   "the",
+  "tig",
+  "til",
+  "time",
   "tl.",
+  "to",
   "tr",
   "tr.",
   "tsd",
   "tsd.",
+  "tur",
   "t\u00e4gl",
   "t\u00e4gl.",
   "t\u00e4glich",
@@ -1114,11 +1388,13 @@
   "ul.",
   "un.",
   "und",
+  "ung",
   "univ",
   "univ.",
   "unter",
   "unter\u2019m",
   "ur.",
+  "ure",
   "usf",
   "usf.",
   "usw",
@@ -1138,7 +1414,11 @@
   "v.v",
   "v_v",
   "value",
+  "value-added",
+  "vel",
+  "ver",
   "vergleiche",
+  "ves",
   "vgl",
   "vgl.",
   "vielleicht",
@@ -1149,6 +1429,7 @@
   "vm.",
   "vol",
   "vol.",
+  "vom",
   "vor",
   "vor\u2019m",
   "vs",
@@ -1157,12 +1438,18 @@
   "w",
   "w.",
   "wSt",
+  "way",
+  "well-established",
+  "wertstabile",
   "wir",
   "wir\u2019s",
   "wiss",
   "wiss.",
+  "with",
+  "wohnimmobilien",
   "x",
   "x'",
+  "x-xxxx",
   "x.",
   "x.X",
   "x.X.",
@@ -1186,16 +1473,23 @@
   "x_x",
   "xd",
   "xdd",
+  "xit",
   "xx",
   "xx.",
+  "xx.x",
   "xxx",
   "xxx.",
   "xxxx",
+  "xxxx)/xxxx",
   "xxxx+",
   "xxxx+/xxxx",
+  "xxxx-xxx",
+  "xxxx-xxxx",
+  "xxxx-xxxx-xxx",
   "xxxx.",
   "xxxx\u2019x",
   "xxx\u2019x",
+  "xx\u0308xxxx",
   "xx\u2019x",
   "x\u2019",
   "x\ufe35x",
@@ -1215,6 +1509,13 @@
   "z.z.",
   "z.zt.",
   "zgl",
+  "ziel-lty",
+  "ziel-netto-irr",
+  "zielanlagestrategie",
+  "zielregionfen)/jand",
+  "zielsektoren",
+  "zielvolumen",
+  "ziirraiaein",
   "zt",
   "zw.",
   "zzgl",
@@ -1236,6 +1537,8 @@
   "\u00b0f.",
   "\u00b0k.",
   "\u00b0x.",
+  "\u00dc",
+  "\u00dcbersicht",
   "\u00e4",
   "\u00e4.",
   "\u00e4gl",
@@ -1249,6 +1552,7 @@
   "\u00fc",
   "\u00fc.",
   "\u00fcber",
+  "\u00fcbersicht",
   "\u00fcber\u2019m",
   "\u0ca0",
   "\u0ca0_\u0ca0",
@@ -1269,6 +1573,8 @@
   "\u2019xx",
   "\u2019xxx",
   "\u2019\u2019",
+  "\u201a",
+  "\u20ac",
   "\u2501",
   "\u253b",
   "\u253b\u2501\u253b",
diff --git a/prototypes/fine_tuning_spaCy/output/model-last/meta.json b/prototypes/fine_tuning_spaCy/output/model-last/meta.json
index ca58b77..daabc76 100644
--- a/prototypes/fine_tuning_spaCy/output/model-last/meta.json
+++ b/prototypes/fine_tuning_spaCy/output/model-last/meta.json
@@ -46,7 +46,7 @@
         "f":1.0
       }
     },
-    "tok2vec_loss":0.000000011,
-    "ner_loss":0.0000000457
+    "tok2vec_loss":0.000000029,
+    "ner_loss":0.0000000614
   }
 }
\ No newline at end of file
diff --git a/prototypes/fine_tuning_spaCy/output/model-last/ner/model b/prototypes/fine_tuning_spaCy/output/model-last/ner/model
index 4909428..8a0c5ae 100644
Binary files a/prototypes/fine_tuning_spaCy/output/model-last/ner/model and b/prototypes/fine_tuning_spaCy/output/model-last/ner/model differ
diff --git a/prototypes/fine_tuning_spaCy/output/model-last/ner/moves b/prototypes/fine_tuning_spaCy/output/model-last/ner/moves
index e27560d..e72ba15 100644
--- a/prototypes/fine_tuning_spaCy/output/model-last/ner/moves
+++ b/prototypes/fine_tuning_spaCy/output/model-last/ner/moves
@@ -1 +1 @@
-��moves�x{"0":{},"1":{"RISIKOPROFIL":20},"2":{"RISIKOPROFIL":20},"3":{"RISIKOPROFIL":20},"4":{"RISIKOPROFIL":20,"":1},"5":{"":1}}�cfg��neg_key�
\ No newline at end of file
+��moves�x{"0":{},"1":{"RISIKOPROFIL":45},"2":{"RISIKOPROFIL":45},"3":{"RISIKOPROFIL":45},"4":{"RISIKOPROFIL":45,"":1},"5":{"":1}}�cfg��neg_key�
\ No newline at end of file
diff --git a/prototypes/fine_tuning_spaCy/output/model-last/tok2vec/model b/prototypes/fine_tuning_spaCy/output/model-last/tok2vec/model
index 0bf1b64..1cfa6a5 100644
Binary files a/prototypes/fine_tuning_spaCy/output/model-last/tok2vec/model and b/prototypes/fine_tuning_spaCy/output/model-last/tok2vec/model differ
diff --git a/prototypes/fine_tuning_spaCy/output/model-last/vocab/strings.json b/prototypes/fine_tuning_spaCy/output/model-last/vocab/strings.json
index 4293997..7569f1d 100644
--- a/prototypes/fine_tuning_spaCy/output/model-last/vocab/strings.json
+++ b/prototypes/fine_tuning_spaCy/output/model-last/vocab/strings.json
@@ -4,6 +4,8 @@
   " ",
   "  ",
   "\"",
+  "$",
+  "%",
   "'",
   "''",
   "'-(",
@@ -46,6 +48,8 @@
   ")/\u00af",
   "):",
   "*",
+  "+",
+  ",",
   "-",
   "-((",
   "-))",
@@ -100,16 +104,40 @@
   ".\u00e4.",
   "/",
   "/3",
+  "/Core+",
+  "/Xxxx+",
+  "/core+",
   "/d",
+  "/xxxx+",
   "0",
+  "0%+",
   "0.0",
   "0.o",
+  "022",
+  "032",
+  "034",
   "0_0",
   "0_o",
   "1",
+  "1.",
+  "10",
+  "12",
+  "2",
+  "2.",
+  "20",
+  "2022",
+  "2032",
+  "2034",
+  "250",
   "3",
+  "3.",
   "33",
   "333",
+  "35",
+  "5",
+  "50",
+  "7",
+  "7,50%+",
   "8",
   "8)",
   "8-",
@@ -234,9 +262,20 @@
   "Abt.",
   "Abteilung",
   "Add",
+  "Aktueller",
+  "Allgemeine",
+  "Amsterdam",
+  "Anlagestrategien",
+  "Anlagevehikels",
+  "Ansprechpartners",
+  "Antagevehikels",
   "Apr",
   "Apr.",
   "April",
+  "Art",
+  "Assets",
+  "Aufl\u00f6sung",
+  "Aufwertung",
   "Aug",
   "Aug.",
   "August",
@@ -250,6 +289,8 @@
   "Bd",
   "Bd.",
   "Beispiel",
+  "Berlin",
+  "Bestandsentwicklungen",
   "Betr",
   "Betr.",
   "Betreff",
@@ -271,6 +312,8 @@
   "Chr.",
   "Cie",
   "Cie.",
+  "Cities",
+  "Closings",
   "Co",
   "Co.",
   "Core",
@@ -279,12 +322,15 @@
   "D",
   "D.",
   "D.C.",
+  "Deutschland",
+  "Deutschlands",
   "Dez",
   "Dez.",
   "Dezember",
   "Di",
   "Di.",
   "Dienstag",
+  "Different",
   "Dipl",
   "Dipl.",
   "Dipl.-Ing",
@@ -294,9 +340,14 @@
   "Donnerstag",
   "Dr",
   "Dr.",
+  "D\u00e4nemark",
   "E",
+  "E-Mail",
   "E.",
+  "Einw",
+  "Europe",
   "European",
+  "Exit",
   "F",
   "F.",
   "FIL",
@@ -310,20 +361,28 @@
   "Februar",
   "Firma",
   "Fond",
+  "Fonds",
   "Fr",
   "Fr.",
+  "Frankreich",
   "Frau",
   "Frl",
   "Frl.",
   "Fr\u00e4ulein",
+  "Fu\u0308hrende",
   "G",
   "G.",
   "G.m.b",
   "G.m.b.H.",
+  "Gateway",
   "Gebr",
   "Gebr.",
+  "Geplantes",
+  "Gesamtrendite",
   "H",
   "H.",
+  "Halten",
+  "Halten-Strategie",
   "Hauptbahnhof",
   "Hbf",
   "Hbf.",
@@ -343,13 +402,21 @@
   "II.",
   "III",
   "III.",
+  "INREV",
+  "IRR",
   "IV",
   "IV.",
+  "Immobilien",
+  "Immobilien-Spezialfonds",
   "Inc",
   "Inc.",
+  "Informationen",
   "Ing",
   "Ing.",
+  "Investmentmanagers",
   "J",
+  "Jahr",
+  "Jahre",
   "Jahrhundert",
   "Jan",
   "Jan.",
@@ -369,16 +436,26 @@
   "K",
   "K.",
   "K.O.",
+  "Kaufen",
+  "Key",
   "L",
   "L'",
   "L.A.",
+  "LTV",
+  "LTY",
+  "Laufzeit",
+  "London",
+  "L\u00e4nderallokation",
   "L\u2019",
   "M",
   "M.",
   "M.A.",
   "M.Sc",
   "M.Sc.",
+  "Manager",
+  "Maximaler",
   "Mehrwertsteuer",
+  "Metropolregionen",
   "Mi",
   "Mi.",
   "Milliarde",
@@ -403,6 +480,9 @@
   "N",
   "N.Y.",
   "N.Y.C.",
+  "Nachvermietungsstrategie",
+  "Name",
+  "Niederlande",
   "Nov",
   "Nov.",
   "November",
@@ -416,14 +496,18 @@
   "O.o",
   "O_O",
   "O_o",
+  "Offen",
+  "Offener",
   "Okt",
   "Okt.",
   "Oktober",
+  "OpCo",
   "Orig",
   "Orig.",
   "Original",
   "P",
   "P.S.",
+  "Paris",
   "Pkt",
   "Pkt.",
   "Prof",
@@ -434,32 +518,44 @@
   "R.",
   "R.I.P.",
   "RE",
+  "REV",
   "RISIKOPROFIL",
   "ROOT",
+  "Rechtsform",
   "Red",
   "Red.",
   "Redaktion",
+  "Risikoprofil",
+  "Risk",
   "S",
   "S'",
   "Sa",
   "Sa.",
   "Samstag",
   "Sc.",
+  "Schweden",
   "Sep",
   "Sep.",
   "Sept",
   "Sept.",
   "September",
+  "Sitz",
+  "Skandinavien",
   "So",
   "So.",
   "Sonntag",
   "St",
   "St.",
+  "Standortaufwertungsstrategie",
+  "Standorte",
   "Std",
   "Std.",
+  "Stil",
   "Str",
   "Str.",
+  "Strategie",
   "Stra\u00dfe",
+  "Struktur",
   "Stunde",
   "S\u2019",
   "T",
@@ -468,6 +564,7 @@
   "Tel",
   "Tel.",
   "Telefon",
+  "Telefonnummer",
   "The",
   "Tr",
   "Tr.",
@@ -488,8 +585,12 @@
   "Value",
   "Vol",
   "Vol.",
+  "W",
+  "Wertstabile",
+  "Wohnimmobilien",
   "X'",
   "X++",
+  "X-Xxxx",
   "X.",
   "X.X",
   "X.X.",
@@ -518,13 +619,25 @@
   "Xxxx",
   "Xxxx+",
   "Xxxx+/Xxxxx",
+  "Xxxx-XXX",
+  "Xxxx-Xxxxx-XXX",
   "Xxxx.",
   "Xxxx.-Xxx",
   "Xxxx.-Xxx.",
   "Xxxxx",
+  "Xxxxx)/Xxxx",
+  "Xxxxx-Xxxxx",
+  "Xx\u0308xxxx",
   "X\u2019",
   "Z",
   "Z.",
+  "Ziel-LTY",
+  "Ziel-Netto-IRR",
+  "Zielanlagestrategie",
+  "Zielregionfen)/Jand",
+  "Zielsektoren",
+  "Zielvolumen",
+  "Ziirraiaein",
   "Zt",
   "Zt.",
   "[",
@@ -578,21 +691,41 @@
   "add",
   "adv",
   "adv.",
+  "ahr",
+  "ail",
+  "aiming",
+  "aktueller",
   "al",
   "al.",
   "allg",
   "allg.",
   "allgemein",
+  "allgemeine",
   "am.",
+  "ame",
+  "amsterdam",
   "an.",
+  "and",
+  "anlagestrategien",
+  "anlagevehikels",
+  "ansprechpartners",
+  "antagevehikels",
   "apr",
   "apr.",
+  "ark",
+  "art",
+  "asset",
+  "assets",
+  "at",
   "at.",
   "ath",
   "auf",
+  "aufl\u00f6sung",
+  "aufwertung",
   "auf\u2019m",
   "aug",
   "aug.",
+  "ausgew\u00e4hlte",
   "ax.",
   "b",
   "b.",
@@ -604,6 +737,8 @@
   "bd.",
   "beispielsweise",
   "ber",
+  "berlin",
+  "bestandsentwicklungen",
   "betr",
   "betr.",
   "beziehungsweise",
@@ -632,23 +767,29 @@
   "c/o",
   "ca",
   "ca.",
+  "cal",
   "cdu",
   "cdu/csu",
   "ce>",
   "chr",
   "chr.",
+  "cht",
   "cie",
   "cie.",
+  "cities",
   "cl.",
+  "closings",
   "co",
   "co.",
   "core",
   "core+",
   "core+/value",
   "csu",
+  "cts",
   "d",
   "d'",
   "d)",
+  "d,dd%+",
   "d-",
   "d-)",
   "d-X",
@@ -661,30 +802,43 @@
   "dX",
   "d_d",
   "d_x",
+  "dam",
   "dd",
   "ddd",
+  "dddd",
   "de",
+  "ded",
   "dem",
+  "den",
+  "der",
   "dergleichen",
+  "des",
+  "deutschland",
+  "deutschlands",
+  "development",
   "dez",
   "dez.",
   "dgl",
   "dgl.",
   "di",
   "di.",
+  "different",
   "dipl",
   "dipl.",
   "dipl.-ing",
   "dipl.-ing.",
   "do",
   "do.",
+  "don",
   "dr",
   "dr.",
   "du",
   "du\u2019s",
   "dv.",
+  "d\u00e4nemark",
   "d\u2019",
   "e",
+  "e-mail",
   "e.",
   "e.V.",
   "e.d",
@@ -699,6 +853,7 @@
   "ebr",
   "ed.",
   "egr",
+  "egy",
   "ehem",
   "ehem.",
   "eigentlich",
@@ -708,12 +863,17 @@
   "eine",
   "einem",
   "einen",
+  "einw",
+  "eit",
   "el.",
+  "els",
   "em.",
   "en.",
   "engl",
   "engl.",
   "englisch",
+  "enhancing",
+  "ent",
   "entspr",
   "entspr.",
   "ep.",
@@ -724,18 +884,23 @@
   "erm.",
   "err",
   "ers",
+  "ersten",
   "er\u2019s",
   "es",
   "etc",
   "etc.",
   "etr",
+  "ets",
+  "europe",
   "european",
   "ev",
   "ev.",
   "eventuell",
   "evtl",
   "evtl.",
+  "exit",
   "expertise",
+  "exposure",
   "ez.",
   "e\u2019s",
   "f",
@@ -746,9 +911,14 @@
   "fam.",
   "feb",
   "feb.",
+  "fen",
+  "festgelegter",
+  "fil",
   "fond",
+  "fonds",
   "fr",
   "fr.",
+  "frankreich",
   "franz\u00f6sisch",
   "frl",
   "frl.",
@@ -756,11 +926,13 @@
   "frz.",
   "fs.",
   "fund",
+  "fu\u0308hrende",
   "f\u2019m",
   "g",
   "g.",
   "g.m.b",
   "g.m.b.h.",
+  "gateway",
   "geb",
   "geb.",
   "gebr",
@@ -772,6 +944,10 @@
   "gegr\u00fcndet",
   "gem",
   "gem.",
+  "gen",
+  "geplantes",
+  "ger",
+  "gesamtrendite",
   "gf.",
   "gfs",
   "ggf",
@@ -780,6 +956,7 @@
   "ggfs.",
   "gg\u00fc",
   "gg\u00fc.",
+  "gie",
   "gl.",
   "good",
   "gr.",
@@ -789,9 +966,12 @@
   "h.",
   "h.c",
   "h.c.",
+  "halten",
+  "halten-strategie",
   "hbf",
   "hbf.",
   "hd.",
+  "hed",
   "hem",
   "hf.",
   "hg",
@@ -799,8 +979,10 @@
   "hil",
   "hinter",
   "hinter\u2019m",
+  "hotels",
   "hr",
   "hr.",
+  "hre",
   "hrn",
   "hrn.",
   "hrsg",
@@ -826,6 +1008,8 @@
   "ich",
   "ich\u2019s",
   "ie.",
+  "ien",
+  "ies",
   "ig.",
   "ihr",
   "ihr\u2019s",
@@ -834,7 +1018,11 @@
   "iii",
   "iii.",
   "il.",
+  "ile",
   "illustration",
+  "ime",
+  "immobilien",
+  "immobilien-spezialfonds",
   "in",
   "in.",
   "inc",
@@ -842,26 +1030,41 @@
   "incl",
   "incl.",
   "ind",
+  "ine",
+  "informationen",
   "ing",
   "ing.",
+  "initiatives",
   "inkl",
   "inkl.",
   "inklusive",
+  "inrev",
   "insb",
   "insb.",
   "insbesondere",
+  "investmentmanagers",
   "investments",
+  "inw",
   "io.",
   "iol",
   "ion",
   "ipl",
+  "irr",
   "is",
   "ise",
+  "isk",
   "iss",
+  "ite",
+  "ith",
+  "ity",
+  "itz",
+  "ium",
   "iv",
   "iv.",
   "j",
   "j.",
+  "jahr",
+  "jahre",
   "jan",
   "jan.",
   "jh",
@@ -882,24 +1085,38 @@
   "kath",
   "kath.",
   "katholisch",
+  "kaufen",
+  "ket",
+  "key",
   "kl.",
   "kt.",
   "l",
   "l'",
   "l.",
   "l.a.",
+  "langfristig",
   "lat",
   "lat.",
+  "laufzeit",
   "laut",
+  "le.g",
+  "ler",
+  "level",
   "lg.",
+  "lin",
   "lio",
   "llg",
   "llt",
   "llv",
+  "london",
   "lt",
   "lt.",
+  "lte",
+  "ltv",
+  "lty",
   "lue",
   "lv.",
+  "l\u00e4nderallokation",
   "l\u2019",
   "m",
   "m.",
@@ -911,19 +1128,30 @@
   "m.m.",
   "m.sc",
   "m.sc.",
+  "mal",
+  "management",
+  "manager",
+  "market",
   "max",
   "max.",
   "maximal",
+  "maximaler",
+  "men",
+  "mer",
+  "metropolregionen",
   "mi",
   "mi.",
+  "million",
   "min",
   "min.",
   "mind",
   "mind.",
   "mindestens",
   "minimal",
+  "minor",
   "mio",
   "mio.",
+  "mit",
   "mo",
   "mo.",
   "monatlich",
@@ -946,18 +1174,26 @@
   "n.r",
   "n.y.",
   "n.y.c.",
+  "nachvermietungsstrategie",
+  "name",
   "nat",
   "nat.",
   "nc.",
   "ncl",
   "nd.",
+  "nde",
+  "nds",
   "ne",
   "nem",
   "nen",
+  "ner",
   "ng.",
   "ngl",
+  "ngs",
+  "niederlande",
   "niv",
   "nkl",
+  "nor",
   "nov",
   "nov.",
   "nr",
@@ -982,23 +1218,32 @@
   "o_o",
   "of",
   "of.",
+  "offen",
+  "offener",
   "og.",
   "okt",
   "okt.",
   "ol.",
   "ond",
   "ood",
+  "opco",
+  "ope",
   "ore",
   "orig",
   "orig.",
   "original",
+  "orm",
   "ov.",
+  "over",
   "p",
   "p.",
   "p.a",
   "p.a.",
   "p.s",
   "p.s.",
+  "pCo",
+  "paris",
+  "pco",
   "pers",
   "pers.",
   "phil",
@@ -1008,26 +1253,35 @@
   "pl.",
   "portfolio",
   "pr.",
+  "premium",
   "prof",
   "prof.",
+  "profile",
+  "projects",
   "pt.",
   "pw.",
   "q",
   "q.",
   "q.e.d",
   "q.e.d.",
+  "quality",
   "r",
   "r.",
   "r.i.p.",
   "rd.",
   "re",
   "re+",
+  "rechtsform",
   "red",
   "red.",
+  "ren",
   "rer",
   "rer.",
+  "rev",
   "rig",
+  "ris",
   "risikoprofil",
+  "risk",
   "rl.",
   "rm.",
   "rn.",
@@ -1035,6 +1289,7 @@
   "rr.",
   "rs.",
   "rsg",
+  "rte",
   "rz.",
   "r\u00f6m",
   "r\u00f6m.",
@@ -1050,6 +1305,7 @@
   "sa",
   "sa.",
   "sb.",
+  "schweden",
   "sd.",
   "sen",
   "sen.",
@@ -1057,10 +1313,13 @@
   "sep.",
   "sept",
   "sept.",
+  "set",
   "sf.",
   "sg.",
   "sie",
   "sie\u2019s",
+  "sitz",
+  "skandinavien",
   "so",
   "so.",
   "sog",
@@ -1072,28 +1331,43 @@
   "ss.",
   "st",
   "st.",
+  "standortaufwertungsstrategie",
+  "standorte",
   "std",
   "std.",
   "stellv",
   "stellv.",
+  "stil",
   "str",
   "str.",
+  "strategie",
+  "strategy",
+  "struktur",
   "sw.",
   "s\u2019",
   "t",
   "t.",
+  "tactical",
   "tc.",
   "td.",
   "tel",
   "tel.",
+  "telefonnummer",
+  "ten",
   "ter",
+  "tes",
   "th.",
   "the",
+  "tig",
+  "til",
+  "time",
   "tl.",
+  "to",
   "tr",
   "tr.",
   "tsd",
   "tsd.",
+  "tur",
   "t\u00e4gl",
   "t\u00e4gl.",
   "t\u00e4glich",
@@ -1114,11 +1388,13 @@
   "ul.",
   "un.",
   "und",
+  "ung",
   "univ",
   "univ.",
   "unter",
   "unter\u2019m",
   "ur.",
+  "ure",
   "usf",
   "usf.",
   "usw",
@@ -1138,7 +1414,11 @@
   "v.v",
   "v_v",
   "value",
+  "value-added",
+  "vel",
+  "ver",
   "vergleiche",
+  "ves",
   "vgl",
   "vgl.",
   "vielleicht",
@@ -1149,6 +1429,7 @@
   "vm.",
   "vol",
   "vol.",
+  "vom",
   "vor",
   "vor\u2019m",
   "vs",
@@ -1157,12 +1438,18 @@
   "w",
   "w.",
   "wSt",
+  "way",
+  "well-established",
+  "wertstabile",
   "wir",
   "wir\u2019s",
   "wiss",
   "wiss.",
+  "with",
+  "wohnimmobilien",
   "x",
   "x'",
+  "x-xxxx",
   "x.",
   "x.X",
   "x.X.",
@@ -1186,16 +1473,23 @@
   "x_x",
   "xd",
   "xdd",
+  "xit",
   "xx",
   "xx.",
+  "xx.x",
   "xxx",
   "xxx.",
   "xxxx",
+  "xxxx)/xxxx",
   "xxxx+",
   "xxxx+/xxxx",
+  "xxxx-xxx",
+  "xxxx-xxxx",
+  "xxxx-xxxx-xxx",
   "xxxx.",
   "xxxx\u2019x",
   "xxx\u2019x",
+  "xx\u0308xxxx",
   "xx\u2019x",
   "x\u2019",
   "x\ufe35x",
@@ -1215,6 +1509,13 @@
   "z.z.",
   "z.zt.",
   "zgl",
+  "ziel-lty",
+  "ziel-netto-irr",
+  "zielanlagestrategie",
+  "zielregionfen)/jand",
+  "zielsektoren",
+  "zielvolumen",
+  "ziirraiaein",
   "zt",
   "zw.",
   "zzgl",
@@ -1236,6 +1537,8 @@
   "\u00b0f.",
   "\u00b0k.",
   "\u00b0x.",
+  "\u00dc",
+  "\u00dcbersicht",
   "\u00e4",
   "\u00e4.",
   "\u00e4gl",
@@ -1249,6 +1552,7 @@
   "\u00fc",
   "\u00fc.",
   "\u00fcber",
+  "\u00fcbersicht",
   "\u00fcber\u2019m",
   "\u0ca0",
   "\u0ca0_\u0ca0",
@@ -1269,6 +1573,8 @@
   "\u2019xx",
   "\u2019xxx",
   "\u2019\u2019",
+  "\u201a",
+  "\u20ac",
   "\u2501",
   "\u253b",
   "\u253b\u2501\u253b",
diff --git a/prototypes/fine_tuning_spaCy/test_model.py b/prototypes/fine_tuning_spaCy/test_model.py
index 8be6f35..7286d43 100644
--- a/prototypes/fine_tuning_spaCy/test_model.py
+++ b/prototypes/fine_tuning_spaCy/test_model.py
@@ -4,7 +4,7 @@ import json
 from pathlib import Path
 
 nlp = spacy.load("output/model-last")
-input_pdf = Path("../../pitch-books/Pitchbook 1.pdf")
+input_pdf = Path("../ocr/output/Pitchbook 1-OCR.pdf")
 doc = fitz.open(input_pdf)
 
 
diff --git a/prototypes/fine_tuning_spaCy/training_data.py b/prototypes/fine_tuning_spaCy/training_data.py
index a491f6b..ed2e4d3 100644
--- a/prototypes/fine_tuning_spaCy/training_data.py
+++ b/prototypes/fine_tuning_spaCy/training_data.py
@@ -1,26 +1,66 @@
 TRAINING_DATA = [
     (
-        "Core",{"entities":[[0,4,"RISIKOPROFIL"]]},
+        "Core",
+        {"entities":[[0,4,"RISIKOPROFIL"]]},
     ),
     (
-        "Core+",{"entities":[[0,5,"RISIKOPROFIL"]]},
+        "Core+",
+        {"entities":[[0,5,"RISIKOPROFIL"]]},
     ),
     (
-        "Core/Core+",{"entities":[[0,10,"RISIKOPROFIL"]]},
+        "Core/Core+",
+        {"entities":[[0,10,"RISIKOPROFIL"]]},
     ),
     (
-        "Value Add",{"entities":[[0,9,"RISIKOPROFIL"]]},
+        "Value Add",
+        {"entities":[[0,9,"RISIKOPROFIL"]]},
     ),
      (
-        "Core/Value Add",{"entities":[[0,14,"RISIKOPROFIL"]]},
+        "Core/Value Add",
+        {"entities":[[0,14,"RISIKOPROFIL"]]},
     ),
      (
-        "Core+/Value Add",{"entities":[[0,15,"RISIKOPROFIL"]]},
+        "Core+/Value Add",
+        {"entities":[[0,15,"RISIKOPROFIL"]]},
     ),
      (
-        "Core/Core+/Value Add",{"entities":[[0,20,"RISIKOPROFIL"]]},
+        "Core/Core+/Value Add",
+        {"entities":[[0,20,"RISIKOPROFIL"]]},
     ),  
     (
-        "The RE portfolio of the fund is a good illustration of Fond expertise in European core/core+ investments .",{"entities":[[82,92,"RISIKOPROFIL"]]},
+        "The RE portfolio of the fund is a good illustration of Fond expertise in European core/core+ investments .",
+        {"entities":[[82,92,"RISIKOPROFIL"]]},
     ),
+    (
+        "Risk level: Core/Core+",
+        {"entities":[[12,22,"RISIKOPROFIL"]]},
+    ),
+     (
+        "Different risk profile (core, core+, value-added)",
+        {"entities":[[24,48,"RISIKOPROFIL"]]},
+    ), 
+    (
+        "Core/Core+ with OpCo premium",
+        {"entities":[[0,10,"RISIKOPROFIL"]]},
+    ),
+     (
+        "Core /Core+ Assets, well-established = Key Gateway Cities in Europe le.g. hotels in the market with minor asset London, Paris, Amsterdam, Berlin] management initiatives",
+        {"entities":[[0,11,"RISIKOPROFIL"]]},
+    ),
+    (
+        "Risikoprofil: Core, Core +",
+        {"entities":[[14,26,"RISIKOPROFIL"]]},
+    ),
+    (
+        "Name des Fonds Name des Investmentmanagers Allgemeine Informationen Name des Ansprechpartners Telefonnummer des Ansprechpartners E-Mail des Ansprechpartners Art des Anlagevehikels Struktur des Anlagevehikels Sitz des Anlagevehikels Struktur des Antagevehikels vom Manager festgelegter Stil Rechtsform Jahr des ersten Closings Laufzeit Geplantes Jahr der Auflösung Ziel-Netto-IRR / Gesamtrendite* Zielvolumen des Anlagevehikels Ziel-LTY ‚Aktueller LTV Ziirraiaein Maximaler LTV Zielregionfen)/Jand Zielsektoren Zielanlagestrategie INREV Fonds Offen Deutschland Core, Core + Offener Immobilien-Spezialfonds 2022 10 - 12 Jahre 2032 - 2034 7,50%+ 250 Mio. € 20% 0% 20% Führende Metropolregionen Deutschlands und ausgewählte Standorte >50T Einw. Wohnimmobilien Wertstabile Wohnimmobilien (mit Bestandsentwicklungen)",
+        {"entities":[[560,572,"RISIKOPROFIL"]]},
+    ),
+    (
+        "Core/Core+ strategy, with tactical exposure to development projects aiming at enhancing the quality of the portfolio over time",
+        {"entities":[[0,10,"RISIKOPROFIL"]]},
+    ),
+    (
+        "Strategie - Übersicht Risikoprofil Core+ Halten-Strategie Kaufen — Halten (langfristig) — Exit 1. Nachvermietungsstrategie Anlagestrategien 2. Standortaufwertungsstrategie 3. Strategie der Aufwertung der Immobilien Niederlande (max. 35 %) Länderallokation Frankreich (max. 35 %) (in % vom Zielvolumen) Skandinavien (Schweden, Dänemark) (max. 35 %) Deutschland (<= 10 %)",
+        {"entities":[[35,40,"RISIKOPROFIL"]]},
+    )
 ] 
\ No newline at end of file