Triple

T13147956
Position Surface form Disambiguated ID Type / Status
Subject Amulet E312388 entity
Predicate producer P490 FINISHED
Object Matthew Wilkinson E872204 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 Wilkinson | Statement: [Amulet, producer, Matthew Wilkinson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matthew Wilkinson
Context triple: [Amulet, producer, Matthew Wilkinson]
  • A. Matthew James Wilkinson chosen
    Matthew James Wilkinson is a film producer known for his work on the British coming-of-age comedy-drama "Days of the Bagnold Summer."
  • B. Ian Wilkinson
    Ian Wilkinson is a video game industry figure best known as the founder of the Canadian game development studio Radical Entertainment.
  • C. Ben Wilkinson
    Ben Wilkinson is a British poet, critic, and academic known for his contemporary poetry collections and contributions to literary journalism.
  • D. Michael Wilkinson
    Michael Wilkinson is a British Labour Party politician who served as Member of Parliament for Ruislip-Northwood from 1997 to 2005.
  • E. Jonathan Peter Wilkinson
    Jonathan Peter Wilkinson is a former English rugby union fly-half renowned for his pivotal role in England's 2003 Rugby World Cup victory, including kicking the winning drop goal in the final.
  • 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_69d806aabde48190899e13e41659cae5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98bd0f5b08190ab700c5de1c8e138 completed April 10, 2026, 11:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6f5da0f708190b848601e571a9fff completed May 3, 2026, 7:14 a.m.
Created at: April 9, 2026, 9:10 p.m.