Triple

T23226532
Position Surface form Disambiguated ID Type / Status
Subject Pardners E581030 entity
Predicate screenwriter P2831 FINISHED
Object Clarence Greene 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: Clarence Greene | Statement: [Pardners, screenwriter, Clarence Greene]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Clarence Greene
Context triple: [Pardners, screenwriter, Clarence Greene]
  • A. Clarence Greene chosen
    Clarence Greene was an American film producer and screenwriter known for his work on mid-20th-century Hollywood crime dramas and Westerns.
  • B. Clarence Rowland
    Clarence Rowland was an American Major League Baseball manager best known for leading the Chicago White Sox to the 1917 World Series championship.
  • C. Charles Furthman
    Charles Furthman was an American screenwriter active during the silent and early sound film era.
  • D. Otis Milburn
    Otis Milburn is the socially awkward yet empathetic teenage protagonist of the British comedy-drama series "Sex Education," known for giving sex advice to his classmates despite his own inexperience.
  • E. Elmer Higgins
    Elmer Higgins is a recurring puppet character on the prank-call comedy television series "Crank Yankers," known for his eccentric and humorous phone antics.
  • 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_69f1922e2d2c81908c0f3fa5df8a5c58 completed April 29, 2026, 5:07 a.m.
Created at: April 17, 2026, 4:09 p.m.