Triple

T12533282
Position Surface form Disambiguated ID Type / Status
Subject Wayne McGregor E299622 entity
Predicate hasCollaboratedWith P8554 FINISHED
Object Thom Yorke E167699 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: Thom Yorke | Statement: [Wayne McGregor, hasCollaboratedWith, Thom Yorke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thom Yorke
Context triple: [Wayne McGregor, hasCollaboratedWith, Thom Yorke]
  • A. Thom Yorke chosen
    Thom Yorke is an English musician best known as the lead singer and principal songwriter of the alternative rock band Radiohead.
  • B. Matthew Yorke
    Matthew Yorke is a British novelist known for his psychologically insightful and often darkly comic fiction.
  • C. James Yorke
    James Yorke is an American mathematician known for coining the term "chaos" in the context of dynamical systems and for his influential work in chaos theory.
  • D. Damon Albarn
    Damon Albarn is an English musician, singer, songwriter, and producer best known as the frontman of Blur and co-creator of the virtual band Gorillaz.
  • E. Jonny Greenwood
    Jonny Greenwood is an English musician and composer best known as the lead guitarist and multi-instrumentalist of the rock band Radiohead and for his acclaimed film scores.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9546b8fd48190ae90e80785b2e2d1 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bc9b9ec8190a25e2658d79836bc completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:57 p.m.