Triple

T10836759
Position Surface form Disambiguated ID Type / Status
Subject Night School E255778 entity
Predicate storyBy P1955 FINISHED
Object Matthew Kellard E891645 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: Matthew Kellard | Statement: [Night School, storyBy, Matthew Kellard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matthew Kellard
Context triple: [Night School, storyBy, Matthew Kellard]
  • A. Matthew Kellard chosen
    Matthew Kellard is a screenwriter known for his work on the film "Night School."
  • B. Mitchell Kennerley
    Mitchell Kennerley was an early 20th-century British-born American publisher and bookseller known for his influential role in modernist literature and fine press publishing.
  • C. Matthew Skemp
    Matthew Skemp is a musician best known as a member of the experimental indie rock band Volcano Choir.
  • D. Matthew Benham
    Matthew Benham is an English professional gambler and businessman best known for using data-driven, analytics-based methods to transform Brentford F.C. from the lower leagues into a successful, Premier League club.
  • E. Matthew Margeson
    Matthew Margeson is an American film composer known for his work on action and genre films, including collaborations on scores for major Hollywood productions.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d746ff70148190b844ab92d796af6c completed April 9, 2026, 6:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2166293808190b7ed1620dfc8a158 completed April 17, 2026, 11:15 a.m.
Created at: April 8, 2026, 9:19 p.m.