Triple

T21561726
Position Surface form Disambiguated ID Type / Status
Subject Keystone comedies E532052 entity
Predicate notableCastMember P7010 FINISHED
Object Al St. John 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: Al St. John | Statement: [Keystone comedies, notableCastMember, Al St. John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Al St. John
Context triple: [Keystone comedies, notableCastMember, Al St. John]
  • A. Al St. John chosen
    Al St. John was an American silent film comedian and actor best known for his slapstick work in early comedies and later as a comic sidekick in Western films.
  • B. Stephen St. John
    Stephen St. John is a film cinematographer best known for his work on the 2003 family adventure movie "Holes."
  • C. Stewart St. John
    Stewart St. John is a television and film writer-producer known for creating and producing genre and drama series, as well as for his work in audio storytelling and digital media.
  • D. David St. John
    David St. John is a pseudonym used by E. Howard Hunt, the American intelligence officer and author involved in the Watergate scandal.
  • E. James Massey
    James Massey was an American information theorist and cryptographer known for his influential contributions to coding theory and cryptographic algorithms.
  • 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_69e0c460db088190828c64206a450273 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eed2e3e2348190b5c3b66cdc871e6e completed April 27, 2026, 3:07 a.m.
Created at: April 16, 2026, 6:29 p.m.