Triple

T23074680
Position Surface form Disambiguated ID Type / Status
Subject Abbott and Costello in the Foreign Legion E575295 entity
Predicate screenwriter P2831 FINISHED
Object John Grant — 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 Grant | Statement: [Abbott and Costello in the Foreign Legion, screenwriter, John Grant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Grant
Context triple: [Abbott and Costello in the Foreign Legion, screenwriter, John Grant]
  • A. John Grant
    John Grant is the protagonist of the Australian film "Red Dog: True Blue," a young boy whose life is transformed through his friendship with the legendary red kelpie.
  • B. John Grant chosen
    John Grant was an American comedy writer best known for crafting many of Abbott and Costello’s film scripts and routines.
  • C. John Grant
    John Grant was a Scottish author, editor, and critic best known for his work in science fiction and fantasy reference books and encyclopedias.
  • D. John Grant
    John Grant was an English Catholic conspirator best known for his involvement in the 1605 Gunpowder Plot to assassinate King James I and blow up the Houses of Parliament.
  • E. John Grant
    John Grant is a British computer programmer best known for his work on the Sinclair ZX80 and ZX81 home computers and for helping create their influential BASIC interpreter.
  • 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_69e245be28d48190ad1348d5a73db37d completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18c61bb7c8190a3d9b1fba173cdff completed April 29, 2026, 4:43 a.m.
Created at: April 17, 2026, 3:56 p.m.