Triple

T22460542
Position Surface form Disambiguated ID Type / Status
Subject Bank of the West E555216 entity
Predicate parentOrganization P254 FINISHED
Object BNP Paribas NE NERFINISHED

How this triple was built (2 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: BNP Paribas | Statement: [Bank of the West, parentOrganization, BNP Paribas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BNP Paribas
Context triple: [Bank of the West, parentOrganization, BNP Paribas]
  • A. BNP Paribas chosen
    BNP Paribas is a major French international banking group and one of the largest financial institutions in Europe.
  • B. Société Générale
    Société Générale is a major French multinational investment and retail bank and financial services company headquartered in Paris.
  • C. Crédit Lyonnais
    Crédit Lyonnais is a major French banking institution, historically state-owned and later privatized, that has played a significant role in France’s financial sector.
  • D. Banque Indosuez
    Banque Indosuez was a major French international banking institution formed through mergers, known for its extensive operations in corporate and investment banking across Europe, Asia, and other global markets.
  • E. Banque du Rhône
    Banque du Rhône is a Swiss banking institution historically active in the Rhône region, providing commercial and private banking services.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e51fdec8190adfdf9f8a6362221 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b7eb5688190bd5e41d4d8189668 completed April 29, 2026, 1:14 a.m.
Created at: April 16, 2026, 8:48 p.m.