Triple

T15674560
Position Surface form Disambiguated ID Type / Status
Subject Peter Farrelly E377405 entity
Predicate wrote P2831 FINISHED
Object Movie 43 E1173138 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: Movie 43 | Statement: [Peter Farrelly, wrote, Movie 43]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Movie 43
Context triple: [Peter Farrelly, wrote, Movie 43]
  • A. Movie 43 chosen
    Movie 43 is a 2013 American anthology comedy film composed of interconnected, raunchy sketch segments featuring an ensemble cast of major Hollywood actors.
  • B. Practical Jokers
    Practical Jokers is an album by the band The Swingers, known for its blend of new wave and pop-rock sounds.
  • C. Kill4Me
    "Kill4Me" is a song by American rock musician Marilyn Manson from his album "Heaven Upside Down."
  • D. The Kentucky Fried Movie
    The Kentucky Fried Movie is a 1977 sketch-comedy film directed by John Landis, known for its raunchy, satirical parodies of television, film, and pop culture.
  • E. Film 44
    Film 44 is a film and television production company founded by director Peter Berg, known for producing action-driven and character-focused projects such as "Battleship" and "Lone Survivor."
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f2c996c8190a9ebe0e92608feaa completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff82ebe98481908d528d2cba485de4 completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 4:16 a.m.