Triple

T23034533
Position Surface form Disambiguated ID Type / Status
Subject Feherty E573556 entity
Predicate hasNotableGuest P10756 FINISHED
Object Graeme McDowell 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: Graeme McDowell | Statement: [Feherty, hasNotableGuest, Graeme McDowell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Graeme McDowell
Context triple: [Feherty, hasNotableGuest, Graeme McDowell]
  • A. Graeme McDowell chosen
    Graeme McDowell is a Northern Irish professional golfer and major champion best known for winning the 2010 U.S. Open and multiple European Tour titles.
  • B. Darren Clarke
    Darren Clarke is a Northern Irish professional golfer best known for winning The Open Championship in 2011 and for his long Ryder Cup career.
  • C. Luke Donald
    Luke Donald is an English professional golfer renowned for reaching world number one and excelling on both the PGA and European Tours.
  • D. Paul Casey
    Paul Casey is an English professional golfer known for his multiple PGA and European Tour victories and consistent presence among the world’s top-ranked players.
  • E. Sergio Garcia
    Sergio García is a Spanish professional motorcycle road racer who competes at the world championship level, particularly known for his performances in the lightweight classes.
  • 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_69e245b911188190bc3d96326c847969 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18483e5848190977b1bdb1b83d187 completed April 29, 2026, 4:09 a.m.
Created at: April 17, 2026, 3:53 p.m.