Triple

T15315688
Position Surface form Disambiguated ID Type / Status
Subject Saving Grace E366150 entity
Predicate producer P490 FINISHED
Object Mark Crowdy E1174668 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: Mark Crowdy | Statement: [Saving Grace, producer, Mark Crowdy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Crowdy
Context triple: [Saving Grace, producer, Mark Crowdy]
  • A. Mark Crowdy chosen
    Mark Crowdy is a British screenwriter and producer best known for creating and writing the crime drama series "Saving Grace."
  • B. Ryan Crocker
    Ryan Crocker is a veteran American diplomat and former U.S. ambassador to multiple Middle Eastern countries, noted for his key role in U.S. foreign policy in the region.
  • C. Eric Crouch
    Eric Crouch is a former American college quarterback best known for his dynamic dual-threat play at the University of Nebraska, where he became one of the nation’s top offensive stars in the early 2000s.
  • D. Chris Ridenhour
    Chris Ridenhour is a film composer known for scoring numerous low-budget genre movies, including works produced by The Asylum.
  • E. Darin Scott
    Darin Scott is an American filmmaker and screenwriter known for his work on crime and thriller films, including co-writing the 2006 action drama "Waist Deep."
  • 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_69d85a121520819093dcce999fdefe1a completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03dd1d384819098f38402a8740d91 completed April 16, 2026, 1:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff9085d388819092be2fd8a0268e23 completed May 9, 2026, 7:52 p.m.
Created at: April 10, 2026, 3:16 a.m.