Triple

T21740321
Position Surface form Disambiguated ID Type / Status
Subject Ken Howard E536638 entity
Predicate appearedIn P795 FINISHED
Object Michael Clayton 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: Michael Clayton | Statement: [Ken Howard, appearedIn, Michael Clayton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Clayton
Context triple: [Ken Howard, appearedIn, Michael Clayton]
  • A. Michael Clayton chosen
    Michael Clayton is a 2007 legal thriller film starring George Clooney as a law firm's "fixer" who confronts a major corporate corruption scandal.
  • B. Billy Flynn
    Billy Flynn is the charismatic, manipulative defense attorney character from the musical "Chicago."
  • C. Citizen Cohn
    Citizen Cohn is a 1986 television film that dramatizes the controversial life and career of lawyer Roy Cohn, a key figure in the McCarthy era.
  • D. Thomas Brennan
    Thomas Brennan was a prominent 19th-century Irish nationalist and land reform activist who played a key leadership role in the Irish Land League.
  • E. Grant Marshall
    Grant Marshall is a British musician and producer best known as a founding member of the influential trip hop group Massive Attack.
  • 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_69e0c46df5448190b4322127ffc4c690 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f01a714c208190b96efe23ed3bf0db completed April 28, 2026, 2:24 a.m.
Created at: April 16, 2026, 6:49 p.m.