Triple

T19152113
Position Surface form Disambiguated ID Type / Status
Subject British Cycling E468833 entity
Predicate notableRiderDeveloped P126235 FINISHED
Object Bradley Wiggins NE NERFINISHED

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: Bradley Wiggins | Statement: [British Cycling, notableRiderDeveloped, Bradley Wiggins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bradley Wiggins
Context triple: [British Cycling, notableRiderDeveloped, Bradley Wiggins]
  • A. Bradley Wiggins chosen
    Bradley Wiggins is a British former professional cyclist renowned for winning the Tour de France and multiple Olympic gold medals, and for his versatility on both track and road.
  • B. Nicholas Froome
    Nicholas Froome is a music producer known for his work on the song "Please."
  • C. Geraint Thomas
    Geraint Thomas is a Welsh professional road cyclist and Tour de France winner known for his Grand Tour successes and long career with Team Sky/INEOS.
  • D. Chris Hoy
    Chris Hoy is a British former track cyclist and multiple Olympic and world champion, widely regarded as one of the most successful cyclists in history.
  • E. Chris Hoy
    Chris Hoy is an American politician who serves as the mayor of Salem, Oregon.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e97dc5a481909a58416126a0862d completed April 20, 2026, 8:53 a.m.
Created at: April 10, 2026, 12:06 p.m.