Triple

T595254
Position Surface form Disambiguated ID Type / Status
Subject Willis Group Holdings E17365 entity
Predicate parentCompanyAfterMerger P5440 FINISHED
Object Willis Towers Watson E74753 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: Willis Towers Watson | Statement: [Willis Group Holdings, parentCompanyAfterMerger, Willis Towers Watson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Willis Towers Watson
Context triple: [Willis Group Holdings, parentCompanyAfterMerger, Willis Towers Watson]
  • A. Towers Watson chosen
    Towers Watson was a global professional services firm specializing in risk management, insurance brokerage, and human capital consulting.
  • B. Willis Group Holdings
    Willis Group Holdings was a global insurance brokerage and risk management firm best known for acquiring the naming rights to Chicago’s Willis Tower (formerly the Sears Tower).
  • C. Aon Corporation
    Aon Corporation is a global professional services firm specializing in risk management, insurance brokerage, and human capital consulting.
  • D. Marsh & McLennan
    Marsh & McLennan is a global professional services firm specializing in insurance brokerage, risk management, and consulting.
  • E. American Financial Group
    American Financial Group is a large U.S. insurance and financial services holding company known for its specialty property and casualty insurance operations.
  • 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_69a49379d09c8190ac7e00b24e2810b1 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49bd280ac8190b6a530ce73da85c8 completed March 1, 2026, 8:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69a529220bc4819087e9de129139b6ef completed March 2, 2026, 6:07 a.m.
Created at: March 1, 2026, 7:33 p.m.