Triple

T23232630
Position Surface form Disambiguated ID Type / Status
Subject Joan Blackman E581201 entity
Predicate coStarredWith P14987 FINISHED
Object Robert Stack 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: Robert Stack | Statement: [Joan Blackman, coStarredWith, Robert Stack]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Stack
Context triple: [Joan Blackman, coStarredWith, Robert Stack]
  • A. Robert Stack chosen
    Robert Stack was an American actor best known for hosting the television series "Unsolved Mysteries" and for his role in the crime drama "The Untouchables."
  • B. Robert Post
    Robert Post is an American legal scholar and former dean of Yale Law School known for his influential work on constitutional law, the First Amendment, and democratic theory.
  • C. Milton Berlinger
    Milton Berlinger, better known by his stage name Milton Berle, was a pioneering American comedian and actor who became one of television’s first major stars.
  • D. Joe Coburn
    Joe Coburn was a 19th-century Irish-American bare-knuckle boxer who became one of the leading heavyweight fighters of his era.
  • E. George Aldrich
    George Aldrich is a NASA contamination control specialist known for his long career testing materials for off-gassing to ensure astronaut safety on space missions.
  • 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f192e70b2c8190abede6e3cd9344f7 completed April 29, 2026, 5:11 a.m.
Created at: April 17, 2026, 4:09 p.m.