Triple

T938251
Position Surface form Disambiguated ID Type / Status
Subject Canary Wharf E20245 entity
Predicate hasOfficeOf P1268 FINISHED
Object MetLife E71892 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: MetLife | Statement: [Canary Wharf, hasOfficeOf, MetLife]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MetLife
Context triple: [Canary Wharf, hasOfficeOf, MetLife]
  • A. MetLife chosen
    MetLife is a major American insurance and financial services company best known for providing life, dental, disability, and other insurance products worldwide.
  • B. John Hancock Mutual Life Insurance Company
    John Hancock Mutual Life Insurance Company was a major American life insurance firm based in Boston, known for its prominent role in the financial services industry and for sponsoring landmark real estate developments.
  • C. Northwestern Mutual
    Northwestern Mutual is a major American financial services and insurance company known for its life insurance, investment, and wealth management products.
  • D. Lincoln Financial Group
    Lincoln Financial Group is a major American financial services company offering insurance, retirement, and investment products.
  • E. Aon Corporation
    Aon Corporation is a global professional services firm specializing in risk management, insurance brokerage, and human capital consulting.
  • 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_69a493b0270c81909e6c9ce310f6aa55 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b74fc204819083dbed5c19c4bc15 completed March 1, 2026, 10:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69a826e0dd188190bf5776a6e4525fdd completed March 4, 2026, 12:34 p.m.
Created at: March 1, 2026, 7:40 p.m.