Triple

T12670456
Position Surface form Disambiguated ID Type / Status
Subject Steve Martin as Roger Cobb E302664 entity
Predicate name P16 FINISHED
Object Roger Cobb E307630 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: Roger Cobb | Statement: [Steve Martin as Roger Cobb, name, Roger Cobb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roger Cobb
Context triple: [Steve Martin as Roger Cobb, name, Roger Cobb]
  • A. Roger Cobb chosen
    Roger Cobb is the harried, skeptical lawyer who becomes comically entangled with a deceased heiress’s spirit in the 1984 fantasy-comedy film "All of Me."
  • B. Billy Keller
    Billy Keller is a former American professional basketball guard best known for his sharpshooting and key role on the Indiana Pacers’ championship teams in the American Basketball Association.
  • C. Chuck Aule
    Chuck Aule is a U.S. Marshal and the investigative partner to Teddy Daniels in the psychological thriller film "Shutter Island."
  • D. Larry Cobb
    Larry Cobb is a musician best known as a member of Kevin Costner's country-rock band, Kevin Costner & Modern West.
  • E. Luke Appling
    Luke Appling was a star shortstop for the Chicago White Sox and a Baseball Hall of Famer known for his exceptional hitting and on-base skills during the 1930s and 1940s.
  • 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_69d7bdee64a08190801c6d470aefd723 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96183a6048190b2ef219eb9d20aa4 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f67c7527c4819096c49a12dcba3c1a completed May 2, 2026, 10:36 p.m.
Created at: April 9, 2026, 5:20 p.m.