Triple

T6889376
Position Surface form Disambiguated ID Type / Status
Subject Amy Madigan E159006 entity
Predicate familyName P18 FINISHED
Object Madigan E514174 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: Madigan | Statement: [Amy Madigan, familyName, Madigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madigan
Context triple: [Amy Madigan, familyName, Madigan]
  • A. Madigan chosen
    Madigan is a 1968 American crime drama film starring Richard Widmark as a tough New York City police detective navigating corruption and moral ambiguity.
  • B. Corrigan
    Corrigan is an Irish-origin surname borne by numerous notable figures in fields such as religion, politics, sports, and entertainment.
  • C. Govandi
    Govandi is a densely populated neighborhood in eastern Mumbai known for its informal settlements, industrial areas, and proximity to major transport routes.
  • D. John Madigan
    John Madigan is an American media executive best known for serving as chairman and CEO of Tribune Company, one of the largest newspaper and broadcasting firms in the United States.
  • E. Mulally
    Mulally is the surname of Alan Mulally, the American engineer and former CEO known for leading major turnarounds at Boeing and Ford Motor Company.
  • 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_69c6883568c8819081db6407e892cccc completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d9117c84819093dad7b765337b63 completed March 27, 2026, 7:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c742e71bcc81908231a861be47b7db completed March 28, 2026, 2:54 a.m.
Created at: March 27, 2026, 2:23 p.m.