Triple

T6069112
Position Surface form Disambiguated ID Type / Status
Subject Duck Soup E135233 entity
Predicate screenwriter P2831 FINISHED
Object Arthur Sheekman E324199 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: Arthur Sheekman | Statement: [Duck Soup, screenwriter, Arthur Sheekman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arthur Sheekman
Context triple: [Duck Soup, screenwriter, Arthur Sheekman]
  • A. Arthur Sheekman chosen
    Arthur Sheekman was an American screenwriter and humorist best known for his work on Marx Brothers films and other Hollywood comedies during the 1930s and 1940s.
  • B. Sidney Buchman
    Sidney Buchman was an American screenwriter and producer best known for his work in Hollywood during the 1930s–1950s, including notable collaborations with major studios and directors.
  • C. Clarence Fahnestock
    Clarence Fahnestock was a New York physician and outdoorsman whose legacy is commemorated by the state park that bears his name.
  • D. Irving Newman
    Irving Newman was an American physician and the father of actor and director Paul Newman.
  • E. George Zuckerman
    George Zuckerman was an American screenwriter and novelist best known for his work on mid-20th-century Hollywood films, including collaborations with director Douglas Sirk.
  • 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_69c00879e8048190b690717d19c5bc03 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c0574157848190bb8e0972eb55a363 completed March 22, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69c750fd986c819099dcf429008e8cdf completed March 28, 2026, 3:54 a.m.
Created at: March 22, 2026, 4:10 p.m.