Triple

T17435675
Position Surface form Disambiguated ID Type / Status
Subject Harry Carey Jr. E423995 entity
Predicate name P16 FINISHED
Object Harry Carey Jr. 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: Harry Carey Jr. | Statement: [Harry Carey Jr., name, Harry Carey Jr.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Carey Jr.
Context triple: [Harry Carey Jr., name, Harry Carey Jr.]
  • A. Harry Carey Jr. chosen
    Harry Carey Jr. was an American character actor best known for his roles in classic Western films, particularly those directed by John Ford.
  • B. Harry Carey
    Harry Carey was an American actor best known as a pioneering star of early Western films and a prominent figure of the silent film era.
  • C. Timothy Carey
    Timothy Carey was an American character actor and filmmaker known for his intense, eccentric performances in mid-20th-century films, including several collaborations with director Stanley Kubrick.
  • D. Alan Cline
    Alan Cline is a computer scientist and academic known for his long-standing faculty role in the Department of Computer Science at the University of Texas at Austin.
  • E. Billy Hartnett
    Billy Hartnett is the commonly used name for William Hartnett, likely referring to him in informal or public contexts.
  • 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_69d889d88b6081908bada047f5b3ba51 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4490361c081908fd24f9a812f212c completed April 19, 2026, 3:16 a.m.
Created at: April 10, 2026, 5:46 a.m.