Triple

T16911912
Position Surface form Disambiguated ID Type / Status
Subject Sean Kelly E410217 entity
Predicate name P16 FINISHED
Object Sean Kelly 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: Sean Kelly | Statement: [Sean Kelly, name, Sean Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sean Kelly
Context triple: [Sean Kelly, name, Sean Kelly]
  • A. Sean Kelly chosen
    Sean Kelly is an Irish former professional cyclist widely regarded as one of the greatest classics riders of all time, known for his dominance in stage races and one-day events during the 1980s.
  • B. Kevin O'Rourke
    Kevin O'Rourke is an American actor best known for his work in television and film, including prominent roles on series such as Remember WENN and Boardwalk Empire.
  • C. Brian Kavanagh
    Brian Kavanagh is a film editor best known for his work on notable Australian and international films, including the drama "The Devil's Playground."
  • D. Brian O’Dowd
    Brian O’Dowd is a television and film producer best known for his work as an executive producer on the series "Nightingale."
  • E. Tim O'Kelly
    Tim O'Kelly is an American actor best known for his role as the young police officer in Peter Bogdanovich's 1968 film "Targets."
  • 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_69d886c7b1e481908c3766dfa8c13458 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3ca3d6be88190bca5e1fdf727141b completed April 18, 2026, 6:15 p.m.
Created at: April 10, 2026, 5:30 a.m.