Triple

T22998056
Position Surface form Disambiguated ID Type / Status
Subject Retief Goosen E572557 entity
Predicate givenName P17 FINISHED
Object Retief 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: Retief | Statement: [Retief Goosen, givenName, Retief]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Retief
Context triple: [Retief Goosen, givenName, Retief]
  • A. Retief
    Retief is an Afrikaans surname of French Huguenot origin, notably borne by South African historical figures and athletes.
  • B. Oosthuizen
    Oosthuizen is a small village in the Dutch province of North Holland, known for its historic church and traditional polder landscape.
  • C. Mitchell Goosen
    Mitchell Goosen is a laid-back, surfing and inline-skating teenager from California who must adapt to life with his relatives in Cincinnati in the 1993 coming-of-age sports comedy "Airborne."
  • D. Retief Goosen chosen
    Retief Goosen is a South African professional golfer and two-time U.S. Open champion known for his smooth putting and success on major international tours.
  • E. Louis Oosthuizen
    Louis Oosthuizen is a South African professional golfer and major champion best known for winning the 2010 Open Championship and finishing runner-up in all four majors.
  • 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_69e245b6a3ac81908087599eefe3e365 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f182f54ce88190930530958e2a1830 completed April 29, 2026, 4:03 a.m.
Created at: April 17, 2026, 3:50 p.m.