Triple

T20561844
Position Surface form Disambiguated ID Type / Status
Subject Ken Kercheval E504860 entity
Predicate coStarredWith P14987 FINISHED
Object Larry Hagman 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: Larry Hagman | Statement: [Ken Kercheval, coStarredWith, Larry Hagman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larry Hagman
Context triple: [Ken Kercheval, coStarredWith, Larry Hagman]
  • A. Larry Hagman chosen
    Larry Hagman was an American actor best known for his iconic role as the scheming oil baron J.R. Ewing on the television series "Dallas."
  • B. Howard Hesseman
    Howard Hesseman was an American actor and comedian best known for his role as DJ Dr. Johnny Fever on the television sitcom "WKRP in Cincinnati."
  • C. William H. Murray
    William H. Murray was an American lawyer and politician who served as the ninth governor of Oklahoma and was a prominent figure in the state’s early political history.
  • D. Gary Chandler
    Gary Chandler is a British guitarist best known for his work with the progressive rock band Jadis.
  • E. Ronald Vernon Newman
    Ronald Vernon Newman was an English-born American soccer coach best known for his pioneering role and success in North American professional and indoor soccer.
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a79ec10481909740eb6a08ae2658 completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.