Triple

T20141107
Position Surface form Disambiguated ID Type / Status
Subject Things Heard & Seen E491165 entity
Predicate starring P1507 FINISHED
Object Michael O’Keefe 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 O’Keefe | Statement: [Things Heard & Seen, starring, Michael O’Keefe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael O’Keefe
Context triple: [Things Heard & Seen, starring, Michael O’Keefe]
  • A. Michael O’Keefe chosen
    Michael O’Keefe is an American actor best known for his role as young caddie Danny Noonan in the classic comedy film "Caddyshack."
  • B. Charles Keefe
    Charles Keefe is a fictional high-profile political figure whose life becomes the focus of an assassination plot in the thriller film "Red Eye."
  • C. Tom Kilpatrick
    Tom Kilpatrick was a screenwriter best known for his work on the 1940 science fiction horror film "Dr. Cyclops."
  • D. James Fogle
    James Fogle was an American writer and former career criminal best known for his semi-autobiographical novel "Drugstore Cowboy," which was adapted into the acclaimed 1989 film.
  • E. Richard J. Donovan
    Richard J. Donovan was a California legislator and public servant after whom the Richard J. Donovan Correctional Facility in San Diego County is named.
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6679b179c8190a9511df8ed82098a completed April 20, 2026, 5:51 p.m.
Created at: April 11, 2026, 11:32 p.m.