Triple

T19657879
Position Surface form Disambiguated ID Type / Status
Subject Robert B. Stearns E471996 entity
Predicate coFounded P104 FINISHED
Object Bear Stearns 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: Bear Stearns | Statement: [Robert B. Stearns, coFounded, Bear Stearns]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bear Stearns
Context triple: [Robert B. Stearns, coFounded, Bear Stearns]
  • A. Bear Stearns chosen
    Bear Stearns was a major American investment bank and brokerage firm that collapsed during the 2008 financial crisis and was acquired by JPMorgan Chase.
  • B. Lehman Brothers
    Lehman Brothers was a major global investment bank whose 2008 bankruptcy became a central event in the global financial crisis.
  • C. Citigroup
    Citigroup is a major American multinational investment bank and financial services corporation headquartered in New York City.
  • D. Washington Mutual
    Washington Mutual was a former major U.S. savings and loan association that became the largest bank failure in American history during the 2008 financial crisis.
  • E. Guggenheim Securities
    Guggenheim Securities is the investment banking and capital markets arm of Guggenheim Partners, providing advisory, financing, and related financial services to corporate and institutional clients.
  • 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_69d8e51395348190ac1416d46dfc6db0 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e641475f408190bd42ef3f8d590719 completed April 20, 2026, 3:07 p.m.
Created at: April 10, 2026, 1:45 p.m.