{"_id": {"$oid": "69d4eb12b877594bc5718cb5"}, "test_id": "T0636", "benchmark": "company_lists", "date": "2026-03-16", "tags": {"document-type": ["book-page"], "writing": ["printed"], "century": [20], "language": ["en", "de"], "layout": ["list"], "entry-type": ["company"], "task": ["information-extraction"]}, "contributors": ["lea_kasper", "sorin_marti"], "hidden": false, "config": {"provider": "anthropic", "model": "claude-opus-4-6", "dataclass": "ListPage", "temperature": 0.5, "role_description": "You are a Historian", "prompt_file": "prompt.txt", "legacy_test": false}, "prompt": "The image you are presented with stems from a digitized book containing lists of companies.\nYour task is to extract structured information about each company listed on the page.\n\nAbout the source:\n- The image stems from a trade index of the British Swiss Chamber of Commerce.\n- The image can show an alphabetical or a thematic list of companies.\n- The companies are mostly located in Switzerland and the UK.\n- The image stems from a trade index between 1925 and 1958.\n- Most pages have one column but some years have two columns.\n- The source itself is in English and German but the company names can be in English, German, French or Italian.\n\nAbout the entries:\n- Each entry describes a single company or person.\n- Alphabetical entries have filling dots between the company name and the page number. Dots and page numbers are not part of the data and should be ignored.\n- Alphabetical entries seldom to never have locations.\n- Thematic entries often have locations.\n- Thematic entries are listed under headings that describe the type of business.\n- Some thematic headings are only references to other headings, e.g. \"X, s. Y\".\n\nAbout the output:\n- Answer in valid JSON. The JSON should be an array of objects with the following fields:\n- The page ID is given as {page_id}.\n- Do not add country information, if it is not directly written with the location.\n\n{\n  \"entry_id\": \"A unique identifier for the entry, e.g. '{page_id}-1'\",\n  \"company_name\": \"The name of the company or person\",\n  \"location\": \"The location of the company, e.g. 'Zurich' or 'London, UK'. If no location is given, set to null.\"\n  ]\n}\n", "results": {"text": "{\"page_id\":\"32\",\"entries\":[{\"entry_id\":\"32-1\",\"company_name\":\"The Commissioner for Commerce for the Union of South Africa\",\"location\":\"5, Via Manzoni, Milan\"},{\"entry_id\":\"32-2\",\"company_name\":\"The Canadian Government Trade Commissioner\",\"location\":\"26 b, Beursplein, Rotterdam\"},{\"entry_id\":\"32-3\",\"company_name\":\"The Basle Warehouse Company Ltd.\",\"location\":\"1, Erlenstrasse, Basle\"},{\"entry_id\":\"32-4\",\"company_name\":\"Canadian Pacific Express Company\",\"location\":\"62\u201465, Charing Cross, Trafalgar Square, London S.W.1\"},{\"entry_id\":\"32-5\",\"company_name\":\"Crowe & Co., Ltd.\",\"location\":\"67, Nauenstrasse, Basle\"},{\"entry_id\":\"32-6\",\"company_name\":\"Danzas & Co., A.-G.\",\"location\":\"Basle\"},{\"entry_id\":\"32-7\",\"company_name\":\"Goth & Co.\",\"location\":\"45, Elisabethenstrasse, Basle\"},{\"entry_id\":\"32-8\",\"company_name\":\"Charles Im Obersteg & Co.\",\"location\":\"30, Aeschengraben, Basle\"},{\"entry_id\":\"32-9\",\"company_name\":\"Imperial Airways, Ltd.\",\"location\":\"Birsfelden Aerodrome, Basle, Switzerland\"},{\"entry_id\":\"32-10\",\"company_name\":\"Jacky, Maeder & Co.\",\"location\":\"Basle\"},{\"entry_id\":\"32-11\",\"company_name\":\"Lavanchy & Co., Successeurs de Perrin & Co.\",\"location\":\"Place de la Gare, Lausanne\"},{\"entry_id\":\"32-12\",\"company_name\":\"Schweiz. Schleppschiffahrtsgenossenschaft\",\"location\":\"5, Bonergasse, Basle\"},{\"entry_id\":\"32-13\",\"company_name\":\"G. van Spyk\",\"location\":\"3, Centralbahnstrasse, Basle\"},{\"entry_id\":\"32-14\",\"company_name\":\"Weltifurrer Internationale Transporte, A. G.\",\"location\":\"8, Pelikanstrasse, Zurich\"},{\"entry_id\":\"32-15\",\"company_name\":\"Soci\u00e9t\u00e9 Anonyme des Aci\u00e9ries ci-devant Georges Fischer\",\"location\":\"Schaffhausen\"},{\"entry_id\":\"32-16\",\"company_name\":\"D. Barnett, Agence Anglo-Suisse\",\"location\":\"Versoix, Geneva\"},{\"entry_id\":\"32-17\",\"company_name\":\"A.-G. Brown, Boveri & Co.\",\"location\":\"Baden, Aargau\"},{\"entry_id\":\"32-18\",\"company_name\":\"Escher, Wyss & Co., A.-G.\",\"location\":\"Zurich\"},{\"entry_id\":\"32-19\",\"company_name\":\"A. & S. Henry & Co., Ltd.\",\"location\":\"Leeds Road, Bradford\"},{\"entry_id\":\"32-20\",\"company_name\":\"Dunlop Pneumatic Co., A. G.\",\"location\":\"56, Holbeinstrasse, Basle\"},{\"entry_id\":\"32-21\",\"company_name\":\"The North British Rubber Company (Continental) Ltd.\",\"location\":\"31, Gl\u00e4rnischstrasse, Zurich\"},{\"entry_id\":\"32-22\",\"company_name\":\"Buser & Keiser & Co., Ltd.\",\"location\":\"Laufenburg\"},{\"entry_id\":\"32-23\",\"company_name\":\"Hanro Knitting Works, Handschin & Ronus, Ltd.\",\"location\":\"Liestal\"}]}", "model": "claude-opus-4-6", "provider": "anthropic", "finish_reason": "tool_use", "usage": {"input_tokens": 2790, "output_tokens": 1051, "total_tokens": 3841, "input_cost_usd": 0.01395, "output_cost_usd": 0.026275000000000003, "estimated_cost_usd": 0.040225000000000004}, "duration": 18.64769148826599, "timestamp": "2026-03-16T15:54:57.754761", "parsed": {"page_id": "32", "entries": [{"entry_id": "32-1", "company_name": "The Commissioner for Commerce for the Union of South Africa", "location": "5, Via Manzoni, Milan"}, {"entry_id": "32-2", "company_name": "The Canadian Government Trade Commissioner", "location": "26 b, Beursplein, Rotterdam"}, {"entry_id": "32-3", "company_name": "The Basle Warehouse Company Ltd.", "location": "1, Erlenstrasse, Basle"}, {"entry_id": "32-4", "company_name": "Canadian Pacific Express Company", "location": "62\u201465, Charing Cross, Trafalgar Square, London S.W.1"}, {"entry_id": "32-5", "company_name": "Crowe & Co., Ltd.", "location": "67, Nauenstrasse, Basle"}, {"entry_id": "32-6", "company_name": "Danzas & Co., A.-G.", "location": "Basle"}, {"entry_id": "32-7", "company_name": "Goth & Co.", "location": "45, Elisabethenstrasse, Basle"}, {"entry_id": "32-8", "company_name": "Charles Im Obersteg & Co.", "location": "30, Aeschengraben, Basle"}, {"entry_id": "32-9", "company_name": "Imperial Airways, Ltd.", "location": "Birsfelden Aerodrome, Basle, Switzerland"}, {"entry_id": "32-10", "company_name": "Jacky, Maeder & Co.", "location": "Basle"}, {"entry_id": "32-11", "company_name": "Lavanchy & Co., Successeurs de Perrin & Co.", "location": "Place de la Gare, Lausanne"}, {"entry_id": "32-12", "company_name": "Schweiz. Schleppschiffahrtsgenossenschaft", "location": "5, Bonergasse, Basle"}, {"entry_id": "32-13", "company_name": "G. van Spyk", "location": "3, Centralbahnstrasse, Basle"}, {"entry_id": "32-14", "company_name": "Weltifurrer Internationale Transporte, A. G.", "location": "8, Pelikanstrasse, Zurich"}, {"entry_id": "32-15", "company_name": "Soci\u00e9t\u00e9 Anonyme des Aci\u00e9ries ci-devant Georges Fischer", "location": "Schaffhausen"}, {"entry_id": "32-16", "company_name": "D. Barnett, Agence Anglo-Suisse", "location": "Versoix, Geneva"}, {"entry_id": "32-17", "company_name": "A.-G. Brown, Boveri & Co.", "location": "Baden, Aargau"}, {"entry_id": "32-18", "company_name": "Escher, Wyss & Co., A.-G.", "location": "Zurich"}, {"entry_id": "32-19", "company_name": "A. & S. Henry & Co., Ltd.", "location": "Leeds Road, Bradford"}, {"entry_id": "32-20", "company_name": "Dunlop Pneumatic Co., A. G.", "location": "56, Holbeinstrasse, Basle"}, {"entry_id": "32-21", "company_name": "The North British Rubber Company (Continental) Ltd.", "location": "31, Gl\u00e4rnischstrasse, Zurich"}, {"entry_id": "32-22", "company_name": "Buser & Keiser & Co., Ltd.", "location": "Laufenburg"}, {"entry_id": "32-23", "company_name": "Hanro Knitting Works, Handschin & Ronus, Ltd.", "location": "Liestal"}]}, "conversation_id": "eac0e8a3-ba7a-48c3-a576-b114d6a339a9", "score": {"f1_score": 0.43, "precision": 0.42857142857142855, "recall": 0.42857142857142855, "true_positives": 30, "false_positives": 40, "false_negatives": 40, "field_scores": {"entries[10].entry_id": {"response": "32-11", "ground_truth": "156089_1321088_41-11", "score": 0.4}, "entries[22].company_name": {"response": "Hanro Knitting Works, Handschin & Ronus, Ltd.", "ground_truth": "Hanro Knitting Works, Handschin & Ronus, Ltd.", "score": 1.0}, "entries[4].company_name": {"response": "Crowe & Co., Ltd.", "ground_truth": "Crowe & Co., Ltd.", "score": 1.0}, "entries[15].location": {"response": "Versoix, Geneva", "ground_truth": "Versoix, Geneva", "score": 1.0}, "entries[18].company_name": {"response": "A. & S. Henry & Co., Ltd.", "ground_truth": "A. & S. Henry & Co., Ltd.", "score": 1.0}, "entries[11].company_name": {"response": "Schweiz. Schleppschiffahrtsgenossenschaft", "ground_truth": "Schweiz. Schleppschiffahrtsgenossenschaft", "score": 1.0}, "entries[14].entry_id": {"response": "32-15", "ground_truth": "156089_1321088_41-15", "score": 0.4}, "entries[22].location": {"response": "Liestal", "ground_truth": "Liestal", "score": 1.0}, "entries[12].company_name": {"response": "G. van Spyk", "ground_truth": "G. van Spyk", "score": 1.0}, "entries[19].company_name": {"response": "Dunlop Pneumatic Co., A. G.", "ground_truth": "Dunlop Pneumatic Co., A. G.", "score": 1.0}, "entries[7].company_name": {"response": "Charles Im Obersteg & Co.", "ground_truth": "Charles Im Obersteg & Co.", "score": 1.0}, "entries[11].entry_id": {"response": "32-12", "ground_truth": "156089_1321088_41-12", "score": 0.4}, "entries[0].company_name": {"response": "The Commissioner for Commerce for the Union of South Africa", "ground_truth": "The Commissioner for Commerce for the Union of South Africa", "score": 1.0}, "entries[22].entry_id": {"response": "32-23", "ground_truth": "156089_1321088_41-23", "score": 0.4}, "entries[5].company_name": {"response": "Danzas & Co., A.-G.", "ground_truth": "Danzas & Co., A.-G.", "score": 1.0}, "entries[4].entry_id": {"response": "32-5", "ground_truth": "156089_1321088_41-5", "score": 0.34782608695652173}, "entries[20].company_name": {"response": "The North British Rubber Company (Continental) Ltd.", "ground_truth": "The North British Rubber Company (Continental) Ltd.", "score": 1.0}, "entries[16].entry_id": {"response": "32-17", "ground_truth": "156089_1321088_41-17", "score": 0.4}, "entries[8].company_name": {"response": "Imperial Airways, Ltd.", "ground_truth": "Imperial Airways, Ltd.", "score": 1.0}, "entries[11].location": {"response": "5, Bonergasse, Basle", "ground_truth": "Basle, Switzerland", "score": 0.368421052631579}, "entries[21].entry_id": {"response": "32-22", "ground_truth": "156089_1321088_41-22", "score": 0.4}, "entries[5].entry_id": {"response": "32-6", "ground_truth": "156089_1321088_41-6", "score": 0.34782608695652173}, "entries[9].location": {"response": "Basle", "ground_truth": "Basle", "score": 1.0}, "entries[2].location": {"response": "1, Erlenstrasse, Basle", "ground_truth": "Basle", "score": 0.3703703703703704}, "entries[5].location": {"response": "Basle", "ground_truth": "Basle", "score": 1.0}, "entries[19].entry_id": {"response": "32-20", "ground_truth": "156089_1321088_41-20", "score": 0.4}, "entries[1].location": {"response": "26 b, Beursplein, Rotterdam", "ground_truth": "Rotterdam", "score": 0.5}, "entries[10].location": {"response": "Place de la Gare, Lausanne", "ground_truth": "Lausanne", "score": 0.4705882352941176}, "entries[1].entry_id": {"response": "32-2", "ground_truth": "156089_1321088_41-2", "score": 0.34782608695652173}, "entries[16].company_name": {"response": "A.-G. Brown, Boveri & Co.", "ground_truth": "A.-G. Brown, Boveri & Co.", "score": 1.0}, "entries[18].entry_id": {"response": "32-19", "ground_truth": "156089_1321088_41-19", "score": 0.4}, "entries[7].entry_id": {"response": "32-8", "ground_truth": "156089_1321088_41-8", "score": 0.34782608695652173}, "entries[3].company_name": {"response": "Canadian Pacific Express Company", "ground_truth": "Canadian Pacific Express Company", "score": 1.0}, "entries[19].location": {"response": "56, Holbeinstrasse, Basle", "ground_truth": "Basle", "score": 0.33333333333333337}, "entries[2].company_name": {"response": "The Basle Warehouse Company Ltd.", "ground_truth": "The Basle Warehouse Company Ltd.", "score": 1.0}, "entries[12].entry_id": {"response": "32-13", "ground_truth": "156089_1321088_41-13", "score": 0.4}, "entries[20].location": {"response": "31, Gl\u00e4rnischstrasse, Zurich", "ground_truth": "Zurich", "score": 0.3529411764705882}, "entries[3].entry_id": {"response": "32-4", "ground_truth": "156089_1321088_41-4", "score": 0.34782608695652173}, "entries[17].location": {"response": "Zurich", "ground_truth": "Zurich", "score": 1.0}, "entries[12].location": {"response": "3, Centralbahnstrasse, Basle", "ground_truth": "Basle", "score": 0.303030303030303}, "entries[16].location": {"response": "Baden, Aargau", "ground_truth": "Baden", "score": 0.5555555555555556}, "entries[10].company_name": {"response": "Lavanchy & Co., Successeurs de Perrin & Co.", "ground_truth": "Lavanchy & Co., Successeurs de Perrin & Co.", "score": 1.0}, "entries[6].entry_id": {"response": "32-7", "ground_truth": "156089_1321088_41-7", "score": 0.34782608695652173}, "entries[4].location": {"response": "67, Nauenstrasse, Basle", "ground_truth": "Basle", "score": 0.3571428571428571}, "entries[17].entry_id": {"response": "32-18", "ground_truth": "156089_1321088_41-18", "score": 0.4}, "entries[14].location": {"response": "Schaffhausen", "ground_truth": "Schaffhausen", "score": 1.0}, "entries[13].location": {"response": "8, Pelikanstrasse, Zurich", "ground_truth": "Zurich", "score": 0.3870967741935484}, "entries[6].location": {"response": "45, Elisabethenstrasse, Basle", "ground_truth": "Basle", "score": 0.2941176470588235}, "entries[13].company_name": {"response": "Weltifurrer Internationale Transporte, A. G.", "ground_truth": "Weltifurrer Internationale Transporte, A. G.", "score": 1.0}, "entries[6].company_name": {"response": "Goth & Co.", "ground_truth": "Goth & Co.", "score": 1.0}, "page_id": {"response": "32", "ground_truth": "156089_1321088_41", "score": 0.21052631578947367}, "entries[21].location": {"response": "Laufenburg", "ground_truth": "Laufenburg", "score": 1.0}, "entries[21].company_name": {"response": "Buser & Keiser & Co., Ltd.", "ground_truth": "Buser & Keiser & Co., Ltd.", "score": 1.0}, "entries[2].entry_id": {"response": "32-3", "ground_truth": "156089_1321088_41-3", "score": 0.34782608695652173}, "entries[8].location": {"response": "Birsfelden Aerodrome, Basle, Switzerland", "ground_truth": "Basle", "score": 0.2222222222222222}, "entries[3].location": {"response": "62\u201465, Charing Cross, Trafalgar Square, London S.W.1", "ground_truth": "London S. W. 1.", "score": 0.35820895522388063}, "entries[9].entry_id": {"response": "32-10", "ground_truth": "156089_1321088_41-10", "score": 0.4}, "entries[18].location": {"response": "Leeds Road, Bradford", "ground_truth": "Bradford", "score": 0.5714285714285714}, "entries[14].company_name": {"response": "Soci\u00e9t\u00e9 Anonyme des Aci\u00e9ries ci-devant Georges Fischer", "ground_truth": "Soci\u00e9t\u00e9 Anonyme des Aci\u00e9ries ci-devant Georges Fischer", "score": 1.0}, "entries[7].location": {"response": "30, Aeschengraben, Basle", "ground_truth": "Basle", "score": 0.3448275862068966}, "entries[0].location": {"response": "5, Via Manzoni, Milan", "ground_truth": "Milan", "score": 0.3846153846153846}, "entries[9].company_name": {"response": "Jacky, Maeder & Co.", "ground_truth": "Jacky, Maeder & Co.", "score": 1.0}, "entries[15].entry_id": {"response": "32-16", "ground_truth": "156089_1321088_41-16", "score": 0.4}, "entries[8].entry_id": {"response": "32-9", "ground_truth": "156089_1321088_41-9", "score": 0.34782608695652173}, "entries[13].entry_id": {"response": "32-14", "ground_truth": "156089_1321088_41-14", "score": 0.4}, "entries[17].company_name": {"response": "Escher, Wyss & Co., A.-G.", "ground_truth": "Escher, Wyss & Co., A.-G.", "score": 1.0}, "entries[0].entry_id": {"response": "32-1", "ground_truth": "156089_1321088_41-1", "score": 0.34782608695652173}, "entries[1].company_name": {"response": "The Canadian Government Trade Commissioner", "ground_truth": "The Canadian Government Trade Commissioner", "score": 1.0}, "entries[20].entry_id": {"response": "32-21", "ground_truth": "156089_1321088_41-21", "score": 0.4}, "entries[15].company_name": {"response": "D. Barnett, Agence Anglo-Suisse", "ground_truth": "D. Barnett, Agence Anglo-Suisse", "score": 1.0}}, "total_fields": 70}, "raw_response": "{\"id\":\"msg_01BMdf4Fw35eqM2zVok26Vdn\",\"content\":[{\"id\":\"toolu_017utk13VV2YQfeAGE1RZmMx\",\"input\":{\"page_id\":\"32\",\"entries\":[{\"entry_id\":\"32-1\",\"company_name\":\"The Commissioner for Commerce for the Union of South Africa\",\"location\":\"5, Via Manzoni, Milan\"},{\"entry_id\":\"32-2\",\"company_name\":\"The Canadian Government Trade Commissioner\",\"location\":\"26 b, Beursplein, Rotterdam\"},{\"entry_id\":\"32-3\",\"company_name\":\"The Basle Warehouse Company Ltd.\",\"location\":\"1, Erlenstrasse, Basle\"},{\"entry_id\":\"32-4\",\"company_name\":\"Canadian Pacific Express Company\",\"location\":\"62\u201465, Charing Cross, Trafalgar Square, London S.W.1\"},{\"entry_id\":\"32-5\",\"company_name\":\"Crowe & Co., Ltd.\",\"location\":\"67, Nauenstrasse, Basle\"},{\"entry_id\":\"32-6\",\"company_name\":\"Danzas & Co., A.-G.\",\"location\":\"Basle\"},{\"entry_id\":\"32-7\",\"company_name\":\"Goth & Co.\",\"location\":\"45, Elisabethenstrasse, Basle\"},{\"entry_id\":\"32-8\",\"company_name\":\"Charles Im Obersteg & Co.\",\"location\":\"30, Aeschengraben, Basle\"},{\"entry_id\":\"32-9\",\"company_name\":\"Imperial Airways, Ltd.\",\"location\":\"Birsfelden Aerodrome, Basle, Switzerland\"},{\"entry_id\":\"32-10\",\"company_name\":\"Jacky, Maeder & Co.\",\"location\":\"Basle\"},{\"entry_id\":\"32-11\",\"company_name\":\"Lavanchy & Co., Successeurs de Perrin & Co.\",\"location\":\"Place de la Gare, Lausanne\"},{\"entry_id\":\"32-12\",\"company_name\":\"Schweiz. Schleppschiffahrtsgenossenschaft\",\"location\":\"5, Bonergasse, Basle\"},{\"entry_id\":\"32-13\",\"company_name\":\"G. van Spyk\",\"location\":\"3, Centralbahnstrasse, Basle\"},{\"entry_id\":\"32-14\",\"company_name\":\"Weltifurrer Internationale Transporte, A. G.\",\"location\":\"8, Pelikanstrasse, Zurich\"},{\"entry_id\":\"32-15\",\"company_name\":\"Soci\u00e9t\u00e9 Anonyme des Aci\u00e9ries ci-devant Georges Fischer\",\"location\":\"Schaffhausen\"},{\"entry_id\":\"32-16\",\"company_name\":\"D. Barnett, Agence Anglo-Suisse\",\"location\":\"Versoix, Geneva\"},{\"entry_id\":\"32-17\",\"company_name\":\"A.-G. Brown, Boveri & Co.\",\"location\":\"Baden, Aargau\"},{\"entry_id\":\"32-18\",\"company_name\":\"Escher, Wyss & Co., A.-G.\",\"location\":\"Zurich\"},{\"entry_id\":\"32-19\",\"company_name\":\"A. & S. Henry & Co., Ltd.\",\"location\":\"Leeds Road, Bradford\"},{\"entry_id\":\"32-20\",\"company_name\":\"Dunlop Pneumatic Co., A. G.\",\"location\":\"56, Holbeinstrasse, Basle\"},{\"entry_id\":\"32-21\",\"company_name\":\"The North British Rubber Company (Continental) Ltd.\",\"location\":\"31, Gl\u00e4rnischstrasse, Zurich\"},{\"entry_id\":\"32-22\",\"company_name\":\"Buser & Keiser & Co., Ltd.\",\"location\":\"Laufenburg\"},{\"entry_id\":\"32-23\",\"company_name\":\"Hanro Knitting Works, Handschin & Ronus, Ltd.\",\"location\":\"Liestal\"}]},\"name\":\"extract_structured_data\",\"type\":\"tool_use\",\"caller\":{\"type\":\"direct\"}}],\"model\":\"claude-opus-4-6\",\"role\":\"assistant\",\"stop_reason\":\"tool_use\",\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"cache_creation\":{\"ephemeral_1h_input_tokens\":0,\"ephemeral_5m_input_tokens\":0},\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"inference_geo\":\"global\",\"input_tokens\":2790,\"output_tokens\":1051,\"server_tool_use\":null,\"service_tier\":\"standard\"}}"}, "scoring": {"f1_micro": 0.5285497726124305, "f1_macro": 0.528, "micro_precision": 0.5298885511651469, "micro_recall": 0.5272177419354839, "total_instances": 15, "total_tp": 523, "total_fp": 464, "total_fn": 469, "cost_summary": {"total_input_tokens": 41619, "total_output_tokens": 13821, "total_tokens": 55440, "input_cost_usd": 0.20809499999999995, "output_cost_usd": 0.345525, "total_cost_usd": 0.55362}}, "normalized_score": 52.800000000000004}