Triple

T13993772
Position Surface form Disambiguated ID Type / Status
Subject Frank E336643 entity
Predicate producer P490 FINISHED
Object Matt Rowe E823830 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: Matt Rowe | Statement: [Frank, producer, Matt Rowe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matt Rowe
Context triple: [Frank, producer, Matt Rowe]
  • A. Matt Rowe chosen
    Matt Rowe is a British music producer and songwriter best known for his work on major pop acts in the 1990s and 2000s.
  • B. Jason Filardi
    Jason Filardi is an American screenwriter best known for writing popular Hollywood comedies, including the hit film "Bringing Down the House."
  • C. Keith Yandle
    Keith Yandle is an American former professional ice hockey defenseman best known for his long NHL career and holding the league’s ironman record for consecutive games played.
  • D. Brian Gionta
    Brian Gionta is an American former professional ice hockey right winger who captained both the Montreal Canadiens and Buffalo Sabres in the NHL and represented the United States in multiple international tournaments.
  • E. Jay Monahan
    Jay Monahan was an American attorney and legal analyst best known as the late husband of television journalist Katie Couric.
  • 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_69d81c639e808190a0e4b4f3d31c6a59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2eb3b5d881909f15a1e08bb202f3 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac9a7e8c8190a0fd0cd67ff50741 completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:19 p.m.