{"_id": {"$oid": "69d4eb12b877594bc5718ae3"}, "test_id": "T0433", "benchmark": "company_lists", "date": "2026-01-24", "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": "mistral", "model": "magistral-medium-2509", "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\":\"{page_id}\",\"entries\":[{\"entry_id\":\"{page_id}-1\",\"company_name\":\"Example Company\",\"location\":\"Zurich\"},{\"entry_id\":\"{page_id}-2\",\"company_name\":\"Another Example\",\"location\":\"London, UK\"}]}", "model": "magistral-medium-2509", "provider": "mistral", "finish_reason": "stop", "usage": {"input_tokens": 548, "output_tokens": 71, "total_tokens": 619, "input_cost_usd": 0.001096, "output_cost_usd": 0.000355, "estimated_cost_usd": 0.001451}, "duration": 0.9121284484863281, "timestamp": "2026-01-24T13:16:03.916417", "parsed": {"page_id": "{page_id}", "entries": [{"entry_id": "{page_id}-1", "company_name": "Example Company", "location": "Zurich"}, {"entry_id": "{page_id}-2", "company_name": "Another Example", "location": "London, UK"}]}, "conversation_id": "930f5428-c39f-4945-8627-674fd819d90b", "score": {"f1_score": 0.0, "precision": 0.0, "recall": 0.0, "true_positives": 0, "false_positives": 7, "false_negatives": 100, "field_scores": {"entries[25].location": {"response": "", "ground_truth": "Zurich 38", "score": 0.0}, "entries[5].company_name": {"response": "", "ground_truth": "Jacky, Maeder & Co.", "score": 0.0}, "entries[19].company_name": {"response": "", "ground_truth": "Morganite Exports Ltd.", "score": 0.0}, "entries[29].entry_id": {"response": "", "ground_truth": "156089_1321099_53-30", "score": 0.0}, "entries[13].location": {"response": "", "ground_truth": "Basle 23", "score": 0.0}, "entries[10].location": {"response": "", "ground_truth": "Basle 23", "score": 0.0}, "entries[8].location": {"response": "", "ground_truth": "Zurich 9", "score": 0.0}, "entries[19].entry_id": {"response": "", "ground_truth": "156089_1321099_53-20", "score": 0.0}, "entries[11].company_name": {"response": "", "ground_truth": "Natural Ltd.", "score": 0.0}, "entries[13].entry_id": {"response": "", "ground_truth": "156089_1321099_53-14", "score": 0.0}, "entries[29].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[28].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[20].entry_id": {"response": "", "ground_truth": "156089_1321099_53-21", "score": 0.0}, "entries[21].entry_id": {"response": "", "ground_truth": "156089_1321099_53-22", "score": 0.0}, "entries[11].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[32].company_name": {"response": "", "ground_truth": "Guhl & Scheibler Ltd.", "score": 0.0}, "entries[4].entry_id": {"response": "", "ground_truth": "156089_1321099_53-5", "score": 0.0}, "entries[0].location": {"response": "Zurich", "ground_truth": "Geneva", "score": 0.0}, "entries[26].location": {"response": "", "ground_truth": "Winterthur", "score": 0.0}, "entries[2].entry_id": {"response": "", "ground_truth": "156089_1321099_53-3", "score": 0.0}, "entries[5].entry_id": {"response": "", "ground_truth": "156089_1321099_53-6", "score": 0.0}, "entries[12].entry_id": {"response": "", "ground_truth": "156089_1321099_53-13", "score": 0.0}, "entries[2].company_name": {"response": "", "ground_truth": "Goth & Co. Ltd.", "score": 0.0}, "entries[16].entry_id": {"response": "", "ground_truth": "156089_1321099_53-17", "score": 0.0}, "entries[20].location": {"response": "", "ground_truth": "Gerlafingen", "score": 0.0}, "entries[31].location": {"response": "", "ground_truth": "Zurich 2", "score": 0.0}, "entries[9].company_name": {"response": "", "ground_truth": "MAT Transport Ltd.", "score": 0.0}, "entries[24].entry_id": {"response": "", "ground_truth": "156089_1321099_53-25", "score": 0.0}, "entries[17].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[23].entry_id": {"response": "", "ground_truth": "156089_1321099_53-24", "score": 0.0}, "entries[18].entry_id": {"response": "", "ground_truth": "156089_1321099_53-19", "score": 0.0}, "entries[31].entry_id": {"response": "", "ground_truth": "156089_1321099_53-32", "score": 0.0}, "entries[8].company_name": {"response": "", "ground_truth": "Marunion S.A.", "score": 0.0}, "entries[21].location": {"response": "", "ground_truth": "Winterthur", "score": 0.0}, "entries[32].entry_id": {"response": "", "ground_truth": "156089_1321099_53-33", "score": 0.0}, "entries[6].entry_id": {"response": "", "ground_truth": "156089_1321099_53-7", "score": 0.0}, "entries[14].entry_id": {"response": "", "ground_truth": "156089_1321099_53-15", "score": 0.0}, "entries[5].location": {"response": "", "ground_truth": "Zurich 1", "score": 0.0}, "entries[10].company_name": {"response": "", "ground_truth": "M\u00fcller-Gysin Ltd.", "score": 0.0}, "entries[13].company_name": {"response": "", "ground_truth": "Roba Shipping Agency & Warehouse Ltd.", "score": 0.0}, "page_id": {"response": "{page_id}", "ground_truth": "156089_1321099_53", "score": 0.07692307692307687}, "entries[19].location": {"response": "", "ground_truth": "London", "score": 0.0}, "entries[1].location": {"response": "London, UK", "ground_truth": "Basle", "score": 0.0}, "entries[20].company_name": {"response": "", "ground_truth": "Louis de Roll Iron Works Ltd.", "score": 0.0}, "entries[18].location": {"response": "", "ground_truth": "Schaffhausen", "score": 0.0}, "entries[30].company_name": {"response": "", "ground_truth": "Aug. Birchmeier's S\u00f6hne", "score": 0.0}, "entries[22].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[25].company_name": {"response": "", "ground_truth": "Emil Flachsmann", "score": 0.0}, "entries[2].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[26].entry_id": {"response": "", "ground_truth": "156089_1321099_53-27", "score": 0.0}, "entries[24].location": {"response": "", "ground_truth": "Zurich 5", "score": 0.0}, "entries[6].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[28].entry_id": {"response": "", "ground_truth": "156089_1321099_53-29", "score": 0.0}, "entries[0].entry_id": {"response": "{page_id}-1", "ground_truth": "156089_1321099_53-1", "score": 0.19999999999999996}, "entries[15].company_name": {"response": "", "ground_truth": "Weltifurrer International Transport Co. Ltd.", "score": 0.0}, "entries[9].entry_id": {"response": "", "ground_truth": "156089_1321099_53-10", "score": 0.0}, "entries[9].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[3].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[25].entry_id": {"response": "", "ground_truth": "156089_1321099_53-26", "score": 0.0}, "entries[7].entry_id": {"response": "", "ground_truth": "156089_1321099_53-8", "score": 0.0}, "entries[0].company_name": {"response": "Example Company", "ground_truth": "General Superintendence Co. Ltd.", "score": 0.25531914893617025}, "entries[16].location": {"response": "", "ground_truth": "Zurich 4", "score": 0.0}, "entries[12].location": {"response": "", "ground_truth": "Geneva", "score": 0.0}, "entries[10].entry_id": {"response": "", "ground_truth": "156089_1321099_53-11", "score": 0.0}, "entries[18].company_name": {"response": "", "ground_truth": "George Fischer Ltd.", "score": 0.0}, "entries[28].company_name": {"response": "", "ground_truth": "P. H. Stehelin & Co. Ltd.", "score": 0.0}, "entries[16].company_name": {"response": "", "ground_truth": "A. Welti-Furrer Ltd.", "score": 0.0}, "entries[26].company_name": {"response": "", "ground_truth": "H. Gallmann & Co.", "score": 0.0}, "entries[8].entry_id": {"response": "", "ground_truth": "156089_1321099_53-9", "score": 0.0}, "entries[29].company_name": {"response": "", "ground_truth": "Gustav Baader", "score": 0.0}, "entries[27].location": {"response": "", "ground_truth": "Malley-Lausanne", "score": 0.0}, "entries[31].company_name": {"response": "", "ground_truth": "J. Coray", "score": 0.0}, "entries[30].location": {"response": "", "ground_truth": "Murgenthal", "score": 0.0}, "entries[6].company_name": {"response": "", "ground_truth": "Jacky, Maeder & Co.", "score": 0.0}, "entries[14].location": {"response": "", "ground_truth": "Geneva", "score": 0.0}, "entries[24].company_name": {"response": "", "ground_truth": "W. Simon", "score": 0.0}, "entries[3].company_name": {"response": "", "ground_truth": "Charles Im Obersteg & Co. Ltd.", "score": 0.0}, "entries[17].company_name": {"response": "", "ground_truth": "World Transport Ltd.", "score": 0.0}, "entries[21].company_name": {"response": "", "ground_truth": "Sulzer Brothers Ltd.", "score": 0.0}, "entries[4].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[15].location": {"response": "", "ground_truth": "Zurich 1", "score": 0.0}, "entries[27].entry_id": {"response": "", "ground_truth": "156089_1321099_53-28", "score": 0.0}, "entries[27].company_name": {"response": "", "ground_truth": "L. E. Michel S.A.", "score": 0.0}, "entries[1].company_name": {"response": "Another Example", "ground_truth": "Gondrand Brothers Ltd.", "score": 0.3783783783783784}, "entries[4].company_name": {"response": "", "ground_truth": "John Im Obersteg & Co. Ltd.", "score": 0.0}, "entries[7].company_name": {"response": "", "ground_truth": "Lavanchy & Co. Ltd.", "score": 0.0}, "entries[23].company_name": {"response": "", "ground_truth": "Marunion S.A.", "score": 0.0}, "entries[22].entry_id": {"response": "", "ground_truth": "156089_1321099_53-23", "score": 0.0}, "entries[7].location": {"response": "", "ground_truth": "Lausanne", "score": 0.0}, "entries[17].entry_id": {"response": "", "ground_truth": "156089_1321099_53-18", "score": 0.0}, "entries[23].location": {"response": "", "ground_truth": "Zurich 9", "score": 0.0}, "entries[30].entry_id": {"response": "", "ground_truth": "156089_1321099_53-31", "score": 0.0}, "entries[12].company_name": {"response": "", "ground_truth": "A. Natural, Le Coultre & Co. Ltd.", "score": 0.0}, "entries[11].entry_id": {"response": "", "ground_truth": "156089_1321099_53-12", "score": 0.0}, "entries[32].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[22].company_name": {"response": "", "ground_truth": "Schubarth & Co.", "score": 0.0}, "entries[3].entry_id": {"response": "", "ground_truth": "156089_1321099_53-4", "score": 0.0}, "entries[1].entry_id": {"response": "{page_id}-2", "ground_truth": "156089_1321099_53-2", "score": 0.19999999999999996}, "entries[14].company_name": {"response": "", "ground_truth": "J. V\u00e9ron, Grauer & Co. Ltd.", "score": 0.0}, "entries[15].entry_id": {"response": "", "ground_truth": "156089_1321099_53-16", "score": 0.0}}, "total_fields": 100}, "raw_response": "{\"id\":\"acb9b631fd3944b88a0329abb2e06d5f\",\"object\":\"chat.completion\",\"model\":\"magistral-medium-2509\",\"usage\":{\"prompt_tokens\":548,\"completion_tokens\":71,\"total_tokens\":619,\"num_cached_tokens\":640},\"created\":1769256963,\"choices\":[{\"index\":0,\"message\":{\"content\":\"{ \\\"page_id\\\": \\\"{page_id}\\\", \\\"entries\\\": [ { \\\"entry_id\\\": \\\"{page_id}-1\\\", \\\"company_name\\\": \\\"Example Company\\\", \\\"location\\\": \\\"Zurich\\\" }, { \\\"entry_id\\\": \\\"{page_id}-2\\\", \\\"company_name\\\": \\\"Another Example\\\", \\\"location\\\": \\\"London, UK\\\" } ] }\",\"tool_calls\":null,\"prefix\":false,\"role\":\"assistant\"},\"finish_reason\":\"stop\"}]}"}, "scoring": {"f1_micro": 0.0, "f1_macro": 0.0, "micro_precision": 0.0, "micro_recall": 0.0, "total_instances": 15, "total_tp": 0, "total_fp": 20, "total_fn": 992, "cost_summary": {"total_input_tokens": 8220, "total_output_tokens": 827, "total_tokens": 9047, "input_cost_usd": 0.01644, "output_cost_usd": 0.004135000000000001, "total_cost_usd": 0.020574999999999996}}, "normalized_score": 0}