{"_id": {"$oid": "69d4eb12b877594bc5718bdd"}, "test_id": "T0573", "benchmark": "company_lists", "date": "2026-01-25", "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-small-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\":[]}", "model": "magistral-small-2509", "provider": "mistral", "finish_reason": "stop", "usage": {"input_tokens": 548, "output_tokens": 14, "total_tokens": 562, "input_cost_usd": 0.000274, "output_cost_usd": 7e-06, "estimated_cost_usd": 0.000281}, "duration": 0.2915382385253906, "timestamp": "2026-01-25T01:55:44.417456", "parsed": {"page_id": "{page_id}", "entries": []}, "conversation_id": "c3f7eb71-de6f-47ab-aa21-1ff7598e20dc", "score": {"f1_score": 0.0, "precision": 0.0, "recall": 0.0, "true_positives": 0, "false_positives": 1, "false_negatives": 139, "field_scores": {"entries[25].location": {"response": "", "ground_truth": "Yeovil, Somerset", "score": 0.0}, "entries[5].company_name": {"response": "", "ground_truth": "Aksa Ltd.", "score": 0.0}, "entries[45].company_name": {"response": "", "ground_truth": "Barco Trading Co. Ltd.", "score": 0.0}, "entries[19].company_name": {"response": "", "ground_truth": "Anderes (Rudolf) A.G.", "score": 0.0}, "entries[29].entry_id": {"response": "", "ground_truth": "156089_1321099_11-30", "score": 0.0}, "entries[13].location": {"response": "", "ground_truth": "Madras, India", "score": 0.0}, "entries[37].company_name": {"response": "", "ground_truth": "Baker (John) & Bessemer Ltd.", "score": 0.0}, "entries[10].location": {"response": "", "ground_truth": "Geneva", "score": 0.0}, "entries[8].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[19].entry_id": {"response": "", "ground_truth": "156089_1321099_11-20", "score": 0.0}, "entries[11].company_name": {"response": "", "ground_truth": "Aluminiumwerke A.G.", "score": 0.0}, "entries[13].entry_id": {"response": "", "ground_truth": "156089_1321099_11-14", "score": 0.0}, "entries[41].company_name": {"response": "", "ground_truth": "Bangerter (A.) & Co. Ltd.", "score": 0.0}, "entries[39].location": {"response": "", "ground_truth": "Sch\u00f6nenwerd", "score": 0.0}, "entries[29].location": {"response": "", "ground_truth": "Steffisburg", "score": 0.0}, "entries[28].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[44].entry_id": {"response": "", "ground_truth": "156089_1321099_11-45", "score": 0.0}, "entries[20].entry_id": {"response": "", "ground_truth": "156089_1321099_11-21", "score": 0.0}, "entries[21].entry_id": {"response": "", "ground_truth": "156089_1321099_11-22", "score": 0.0}, "entries[11].location": {"response": "", "ground_truth": "Rorschach", "score": 0.0}, "entries[32].company_name": {"response": "", "ground_truth": "Aubry Brothers, Ciny Watch Ltd.", "score": 0.0}, "entries[4].entry_id": {"response": "", "ground_truth": "156089_1321099_11-5", "score": 0.0}, "entries[34].entry_id": {"response": "", "ground_truth": "156089_1321099_11-35", "score": 0.0}, "entries[42].company_name": {"response": "", "ground_truth": "Banque Galland & Co. S.A.", "score": 0.0}, "entries[0].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[26].location": {"response": "", "ground_truth": "Morley, Yorks", "score": 0.0}, "entries[2].entry_id": {"response": "", "ground_truth": "156089_1321099_11-3", "score": 0.0}, "entries[5].entry_id": {"response": "", "ground_truth": "156089_1321099_11-6", "score": 0.0}, "entries[12].entry_id": {"response": "", "ground_truth": "156089_1321099_11-13", "score": 0.0}, "entries[2].company_name": {"response": "", "ground_truth": "Adam & Co. Ltd.", "score": 0.0}, "entries[41].location": {"response": "", "ground_truth": "Lyss", "score": 0.0}, "entries[16].entry_id": {"response": "", "ground_truth": "156089_1321099_11-17", "score": 0.0}, "entries[35].entry_id": {"response": "", "ground_truth": "156089_1321099_11-36", "score": 0.0}, "entries[20].location": {"response": "", "ground_truth": "Lausanne", "score": 0.0}, "entries[31].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[44].location": {"response": "", "ground_truth": "London", "score": 0.0}, "entries[9].company_name": {"response": "", "ground_truth": "Aluminium Commercial S.A.", "score": 0.0}, "entries[24].entry_id": {"response": "", "ground_truth": "156089_1321099_11-25", "score": 0.0}, "entries[36].location": {"response": "", "ground_truth": "Geneva", "score": 0.0}, "entries[17].location": {"response": "", "ground_truth": "Rorschach", "score": 0.0}, "entries[23].entry_id": {"response": "", "ground_truth": "156089_1321099_11-24", "score": 0.0}, "entries[18].entry_id": {"response": "", "ground_truth": "156089_1321099_11-19", "score": 0.0}, "entries[35].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[31].entry_id": {"response": "", "ground_truth": "156089_1321099_11-32", "score": 0.0}, "entries[8].company_name": {"response": "", "ground_truth": "Albiswerk Zurich A.G.", "score": 0.0}, "entries[21].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[32].entry_id": {"response": "", "ground_truth": "156089_1321099_11-33", "score": 0.0}, "entries[6].entry_id": {"response": "", "ground_truth": "156089_1321099_11-7", "score": 0.0}, "entries[14].entry_id": {"response": "", "ground_truth": "156089_1321099_11-15", "score": 0.0}, "entries[38].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[5].location": {"response": "", "ground_truth": "W\u00fcrenlos, Aargau", "score": 0.0}, "entries[10].company_name": {"response": "", "ground_truth": "Aluminium Limited (Canada) S.A.", "score": 0.0}, "entries[13].company_name": {"response": "", "ground_truth": "Amalgamations Ltd.", "score": 0.0}, "page_id": {"response": "{page_id}", "ground_truth": "156089_1321099_11", "score": 0.07692307692307687}, "entries[19].location": {"response": "", "ground_truth": "St. Gallen", "score": 0.0}, "entries[37].entry_id": {"response": "", "ground_truth": "156089_1321099_11-38", "score": 0.0}, "entries[1].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[20].company_name": {"response": "", "ground_truth": "Andr\u00e9 & Co. Ltd.", "score": 0.0}, "entries[18].location": {"response": "", "ground_truth": "Schaffhausen", "score": 0.0}, "entries[30].company_name": {"response": "", "ground_truth": "Atlantis Verlag A.G.", "score": 0.0}, "entries[22].location": {"response": "", "ground_truth": "Lausanne", "score": 0.0}, "entries[25].company_name": {"response": "", "ground_truth": "Aplin & Barrett Ltd.", "score": 0.0}, "entries[2].location": {"response": "", "ground_truth": "Port Louis, Mauritius", "score": 0.0}, "entries[26].entry_id": {"response": "", "ground_truth": "156089_1321099_11-27", "score": 0.0}, "entries[44].company_name": {"response": "", "ground_truth": "Barclays Bank Ltd.", "score": 0.0}, "entries[24].location": {"response": "", "ground_truth": "Solothurn", "score": 0.0}, "entries[34].location": {"response": "", "ground_truth": "Bienne", "score": 0.0}, "entries[6].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[28].entry_id": {"response": "", "ground_truth": "156089_1321099_11-29", "score": 0.0}, "entries[0].entry_id": {"response": "", "ground_truth": "156089_1321099_11-1", "score": 0.0}, "entries[15].company_name": {"response": "", "ground_truth": "Amida Ltd.", "score": 0.0}, "entries[9].entry_id": {"response": "", "ground_truth": "156089_1321099_11-10", "score": 0.0}, "entries[9].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[3].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[25].entry_id": {"response": "", "ground_truth": "156089_1321099_11-26", "score": 0.0}, "entries[38].entry_id": {"response": "", "ground_truth": "156089_1321099_11-39", "score": 0.0}, "entries[7].entry_id": {"response": "", "ground_truth": "156089_1321099_11-8", "score": 0.0}, "entries[41].entry_id": {"response": "", "ground_truth": "156089_1321099_11-42", "score": 0.0}, "entries[0].company_name": {"response": "", "ground_truth": "Abegg & Co. Ltd.", "score": 0.0}, "entries[16].location": {"response": "", "ground_truth": "Bienne", "score": 0.0}, "entries[40].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[12].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[10].entry_id": {"response": "", "ground_truth": "156089_1321099_11-11", "score": 0.0}, "entries[18].company_name": {"response": "", "ground_truth": "Amsler (Alfred J.) & Co.", "score": 0.0}, "entries[33].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[28].company_name": {"response": "", "ground_truth": "Association of Swiss Machine Tool and Tool Dealers", "score": 0.0}, "entries[45].entry_id": {"response": "", "ground_truth": "156089_1321099_11-46", "score": 0.0}, "entries[16].company_name": {"response": "", "ground_truth": "Amidro (Swiss Druggists' & Chem. Purchasing Assoc.)", "score": 0.0}, "entries[26].company_name": {"response": "", "ground_truth": "Appleyard (John W.) & Sons Ltd.", "score": 0.0}, "entries[40].entry_id": {"response": "", "ground_truth": "156089_1321099_11-41", "score": 0.0}, "entries[8].entry_id": {"response": "", "ground_truth": "156089_1321099_11-9", "score": 0.0}, "entries[29].company_name": {"response": "", "ground_truth": "\u00abAstra\u00bb Fat & Oil Works Ltd.", "score": 0.0}, "entries[38].company_name": {"response": "", "ground_truth": "Bally (C. F.) Ltd.", "score": 0.0}, "entries[27].location": {"response": "", "ground_truth": "Geneva", "score": 0.0}, "entries[42].entry_id": {"response": "", "ground_truth": "156089_1321099_11-43", "score": 0.0}, "entries[31].company_name": {"response": "", "ground_truth": "Attenhofer (A.)", "score": 0.0}, "entries[30].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[6].company_name": {"response": "", "ground_truth": "Albeko Shoe Machinery Ltd.", "score": 0.0}, "entries[33].entry_id": {"response": "", "ground_truth": "156089_1321099_11-34", "score": 0.0}, "entries[14].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[24].company_name": {"response": "", "ground_truth": "Anselmi jr. (Carl)", "score": 0.0}, "entries[3].company_name": {"response": "", "ground_truth": "Adroka Ltd.", "score": 0.0}, "entries[36].entry_id": {"response": "", "ground_truth": "156089_1321099_11-37", "score": 0.0}, "entries[37].location": {"response": "", "ground_truth": "Rotherham", "score": 0.0}, "entries[36].company_name": {"response": "", "ground_truth": "Baezner & Co.", "score": 0.0}, "entries[43].entry_id": {"response": "", "ground_truth": "156089_1321099_11-44", "score": 0.0}, "entries[33].company_name": {"response": "", "ground_truth": "Baader (Gustav)", "score": 0.0}, "entries[43].company_name": {"response": "", "ground_truth": "Banque de Paris et des Pays Bas S.A.", "score": 0.0}, "entries[43].location": {"response": "", "ground_truth": "Geneva", "score": 0.0}, "entries[17].company_name": {"response": "", "ground_truth": "Ampack, Hungerb\u00fchler & Lemm K.G.", "score": 0.0}, "entries[21].company_name": {"response": "", "ground_truth": "Angst & Pfister Ltd.", "score": 0.0}, "entries[4].location": {"response": "", "ground_truth": "Zurich", "score": 0.0}, "entries[15].location": {"response": "", "ground_truth": "Grenchen", "score": 0.0}, "entries[27].entry_id": {"response": "", "ground_truth": "156089_1321099_11-28", "score": 0.0}, "entries[27].company_name": {"response": "", "ground_truth": "Arts M\u00e9nagers S.A.", "score": 0.0}, "entries[1].company_name": {"response": "", "ground_truth": "Acontra A.G.", "score": 0.0}, "entries[4].company_name": {"response": "", "ground_truth": "Aebi (Robert) Ltd.", "score": 0.0}, "entries[35].company_name": {"response": "", "ground_truth": "Bachofen (Willy A.)", "score": 0.0}, "entries[45].location": {"response": "", "ground_truth": "Geneva", "score": 0.0}, "entries[34].company_name": {"response": "", "ground_truth": "Bachmann (Henri)", "score": 0.0}, "entries[7].company_name": {"response": "", "ground_truth": "Albion House Ltd.", "score": 0.0}, "entries[23].company_name": {"response": "", "ground_truth": "Anra S. \u00e0 r. l.", "score": 0.0}, "entries[39].company_name": {"response": "", "ground_truth": "Bally's Shoe Factories Ltd.", "score": 0.0}, "entries[22].entry_id": {"response": "", "ground_truth": "156089_1321099_11-23", "score": 0.0}, "entries[7].location": {"response": "", "ground_truth": "Lausanne", "score": 0.0}, "entries[17].entry_id": {"response": "", "ground_truth": "156089_1321099_11-18", "score": 0.0}, "entries[39].entry_id": {"response": "", "ground_truth": "156089_1321099_11-40", "score": 0.0}, "entries[23].location": {"response": "", "ground_truth": "Territet-Montreux", "score": 0.0}, "entries[42].location": {"response": "", "ground_truth": "Lausanne", "score": 0.0}, "entries[30].entry_id": {"response": "", "ground_truth": "156089_1321099_11-31", "score": 0.0}, "entries[40].company_name": {"response": "", "ground_truth": "B\u00e2loise Marine Insurance Co. Ltd.", "score": 0.0}, "entries[12].company_name": {"response": "", "ground_truth": "Aluminium Industrie A.G.", "score": 0.0}, "entries[11].entry_id": {"response": "", "ground_truth": "156089_1321099_11-12", "score": 0.0}, "entries[32].location": {"response": "", "ground_truth": "Le Noirmont", "score": 0.0}, "entries[22].company_name": {"response": "", "ground_truth": "Annabelle (Fran\u00e7ois Bloch)", "score": 0.0}, "entries[3].entry_id": {"response": "", "ground_truth": "156089_1321099_11-4", "score": 0.0}, "entries[1].entry_id": {"response": "", "ground_truth": "156089_1321099_11-2", "score": 0.0}, "entries[14].company_name": {"response": "", "ground_truth": "Amag Automobil- und Motoren A.G.", "score": 0.0}, "entries[15].entry_id": {"response": "", "ground_truth": "156089_1321099_11-16", "score": 0.0}}, "total_fields": 139}, "raw_response": "{\"id\":\"18040a217087452eb25e64fcb0719d13\",\"object\":\"chat.completion\",\"model\":\"magistral-small-2509\",\"usage\":{\"prompt_tokens\":548,\"completion_tokens\":14,\"total_tokens\":562,\"num_cached_tokens\":640},\"created\":1769302544,\"choices\":[{\"index\":0,\"message\":{\"content\":\"{\\\"page_id\\\": \\\"{page_id}\\\", \\\"entries\\\": []}\",\"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": 10, "total_fn": 992, "cost_summary": {"total_input_tokens": 8220, "total_output_tokens": 756, "total_tokens": 8976, "input_cost_usd": 0.00411, "output_cost_usd": 0.0003780000000000001, "total_cost_usd": 0.004488}}, "normalized_score": 0}