Triple

T21150953
Position Surface form Disambiguated ID Type / Status
Subject Deux-Sèvres E521185 entity
Predicate ISO3166-2Code P208 FINISHED
Object FR-79
FR-79 is the ISO 3166-2 code designating the French department of Deux-Sèvres in western France.
 E1468532 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: FR-79 | Statement: [Deux-Sèvres, ISO3166-2Code, FR-79]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FR-79
Context triple: [Deux-Sèvres, ISO3166-2Code, FR-79]
  • A. FR-77
    FR-77 is the ISO 3166-2 code designating the French department of Seine-et-Marne in the Île-de-France region.
  • B. FR-87
    FR-87 is the ISO 3166-2 code designating the Haute-Vienne department in west-central France.
  • C. FR-90
    FR-90 is the ISO 3166-2 subdivision code assigned to the Territoire de Belfort department in northeastern France.
  • D. FR-59
    FR-59 is the ISO 3166-2 code for Nord, a department in northern France known for its industrial history and proximity to Belgium.
  • E. FR-82
    FR-82 is the ISO 3166-2 code designating the French department of Tarn-et-Garonne in the Occitanie region of southern France.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: FR-79
Triple: [Deux-Sèvres, ISO3166-2Code, FR-79]
Generated description
FR-79 is the ISO 3166-2 code designating the French department of Deux-Sèvres in western France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FR-79
Target entity description: FR-79 is the ISO 3166-2 code designating the French department of Deux-Sèvres in western France.
  • A. FR-77
    FR-77 is the ISO 3166-2 code designating the French department of Seine-et-Marne in the Île-de-France region.
  • B. FR-87
    FR-87 is the ISO 3166-2 code designating the Haute-Vienne department in west-central France.
  • C. FR-90
    FR-90 is the ISO 3166-2 subdivision code assigned to the Territoire de Belfort department in northeastern France.
  • D. FR-59
    FR-59 is the ISO 3166-2 code for Nord, a department in northern France known for its industrial history and proximity to Belgium.
  • E. FR-82
    FR-82 is the ISO 3166-2 code designating the French department of Tarn-et-Garonne in the Occitanie region of southern France.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e0b50c6a848190a4e525a77a319b8a completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e72401830c8190a2008c40c4174d97 completed April 21, 2026, 7:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a096dc839c88190be097464d8a641b3 completed May 17, 2026, 7:27 a.m.
NEDg Description generation batch_6a096e90901081909f96dcf0a7acb6cd completed May 17, 2026, 7:30 a.m.
NED2 Entity disambiguation (via description) batch_6a096f0ce3bc8190a5a82d718a898e13 completed May 17, 2026, 7:32 a.m.
Created at: April 16, 2026, 2:58 p.m.