Triple

T19915014
Position Surface form Disambiguated ID Type / Status
Subject Watership Down (1978 film) E478642 entity
Predicate coDirector P17194 FINISHED
Object John Hubley 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: John Hubley | Statement: [Watership Down (1978 film), coDirector, John Hubley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Hubley
Context triple: [Watership Down (1978 film), coDirector, John Hubley]
  • A. John Hubley chosen
    John Hubley was an influential American animator and director known for his innovative work at UPA and for co-creating distinctive, modernist animated films and characters.
  • B. Charles Gillibert
    Charles Gillibert is a French film producer known for backing acclaimed auteur-driven films such as "Clouds of Sils Maria," "Personal Shopper," and "Mustang."
  • C. Paul Lovett
    Paul Lovett is a film screenwriter best known for co-writing the action drama movie "Four Brothers."
  • D. Frank Parkinson
    Frank Parkinson was a prominent British industrialist and philanthropist whose contributions to education led to major university buildings being named in his honor.
  • E. Charles Aidman
    Charles Aidman was an American character actor and voice artist best known for his extensive work in film and television from the 1950s through the 1980s.
  • 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_69d8e521855c8190b41871700afc8d6a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6599394f081909246006c2e83bacc completed April 20, 2026, 4:51 p.m.
Created at: April 10, 2026, 1:53 p.m.