Triple

T14569153
Position Surface form Disambiguated ID Type / Status
Subject DELAG E341863 entity
Predicate foundedBy P104 FINISHED
Object Banque de la Corrèze
Banque de la Corrèze was a regional French bank that operated in the Corrèze area, providing local financial and banking services.
 E1168983 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: Banque de la Corrèze | Statement: [DELAG, foundedBy, Banque de la Corrèze]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Banque de la Corrèze
Context triple: [DELAG, foundedBy, Banque de la Corrèze]
  • A. Banque de la Dordogne
    Banque de la Dordogne was a regional French bank that operated in the Dordogne area, providing local financial and banking services.
  • B. Banque de la Creuse
    Banque de la Creuse was a regional French bank that operated in the Creuse department, providing local financial and banking services.
  • C. Banque de la Vienne
    Banque de la Vienne was a French regional bank that played a role in local finance and industry development in the Vienne area.
  • D. Banque de la Charente
    Banque de la Charente is a French regional bank that historically operated in the Charente area, providing financial and commercial banking services.
  • E. Banque de l’Oise
    Banque de l’Oise was a regional French bank that played a role in local finance and industry development in the Oise department.
  • 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: Banque de la Corrèze
Triple: [DELAG, foundedBy, Banque de la Corrèze]
Generated description
Banque de la Corrèze was a regional French bank that operated in the Corrèze area, providing local financial and banking services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Banque de la Corrèze
Target entity description: Banque de la Corrèze was a regional French bank that operated in the Corrèze area, providing local financial and banking services.
  • A. Banque de la Dordogne
    Banque de la Dordogne was a regional French bank that operated in the Dordogne area, providing local financial and banking services.
  • B. Banque de la Creuse
    Banque de la Creuse was a regional French bank that operated in the Creuse department, providing local financial and banking services.
  • C. Banque de la Vienne
    Banque de la Vienne was a French regional bank that played a role in local finance and industry development in the Vienne area.
  • D. Banque de la Charente
    Banque de la Charente is a French regional bank that historically operated in the Charente area, providing financial and commercial banking services.
  • E. Banque de l’Oise
    Banque de l’Oise was a regional French bank that played a role in local finance and industry development in the Oise department.
  • 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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb3f2121481908f2385637944785d completed April 14, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff677b7be08190afc2767835836908 completed May 9, 2026, 4:57 p.m.
NEDg Description generation batch_69ff67f64d2c81908fd2d8a09cd0b369 completed May 9, 2026, 4:59 p.m.
NED2 Entity disambiguation (via description) batch_69ff6888a85481909e8cdd34ed230fa4 completed May 9, 2026, 5:02 p.m.
Created at: April 10, 2026, 1:23 a.m.