Triple

T17012415
Position Surface form Disambiguated ID Type / Status
Subject Come What May E412732 entity
Predicate producer P490 FINISHED
Object Craig Armstrong E48032 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: Craig Armstrong | Statement: [Come What May, producer, Craig Armstrong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Craig Armstrong
Context triple: [Come What May, producer, Craig Armstrong]
  • A. Craig Armstrong chosen
    Craig Armstrong is a Scottish composer and arranger renowned for his emotive film scores and orchestral works, including music for major films such as "Love Actually," "Moulin Rouge!" and "The Great Gatsby."
  • B. Craig Armstrong
    Craig Armstrong is a television producer best known for his work as an executive producer on popular reality and home-renovation series.
  • C. Scot Armstrong
    Scot Armstrong is an American screenwriter and producer known for his work on hit comedy films such as "Old School," "Road Trip," and "The Hangover Part II."
  • D. David Armstrong
    David Armstrong is a relatively common personal name shared by various individuals across fields such as sports, academia, and the arts.
  • E. Scott Armstrong
    Scott Armstrong is an American journalist and author known for his investigative reporting and coauthoring influential books on U.S. government and the Supreme Court.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d47cc17c819087f7bd27582bcbfa completed April 18, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b4990948190861ff81f8fc3e8f2 completed May 10, 2026, 11:56 p.m.
Created at: April 10, 2026, 5:33 a.m.