Triple

T1151498
Position Surface form Disambiguated ID Type / Status
Subject CAC 40 E23686 entity
Predicate hasComponent P35 FINISHED
Object Société Générale E111737 NE FINISHED

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: Société Générale | Statement: [CAC 40, hasComponent, Société Générale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Société Générale
Context triple: [CAC 40, hasComponent, Société Générale]
  • A. Société Générale chosen
    Société Générale is a major French multinational investment and retail bank and financial services company headquartered in Paris.
  • B. BNP Paribas
    BNP Paribas is a major French international banking group and one of the largest financial institutions in Europe.
  • C. Rothschild & Cie Banque
    Rothschild & Cie Banque is a prominent French investment bank known for its advisory work on major mergers, acquisitions, and financial transactions.
  • D. Caisse des Dépôts et Consignations
    Caisse des Dépôts et Consignations is a French public financial institution that manages long-term investments and savings on behalf of the state and public interest missions.
  • E. Bouygues
    Bouygues is a major French industrial group primarily active in construction, real estate development, media, and telecommunications.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a493f0d32c8190ac74bad3c87f2641 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bc744e7c81908f8612f2aad28600 completed March 1, 2026, 10:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac667a61248190b71033daadef58e3 completed March 7, 2026, 5:55 p.m.
Created at: March 1, 2026, 7:44 p.m.