Triple

T16262085
Position Surface form Disambiguated ID Type / Status
Subject Stefan Struve E394778 entity
Predicate name P16 FINISHED
Object Stefan Struve E394778 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: Stefan Struve | Statement: [Stefan Struve, name, Stefan Struve]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stefan Struve
Context triple: [Stefan Struve, name, Stefan Struve]
  • A. Stefan Struve chosen
    Stefan Struve is a Dutch mixed martial artist and former UFC heavyweight known for his exceptional height and long reach.
  • B. Tito Ortiz
    Tito Ortiz is an American mixed martial artist and former UFC Light Heavyweight Champion known as one of the promotion’s early stars and most polarizing personalities.
  • C. Fedor Emelianenko
    Fedor Emelianenko is a legendary Russian mixed martial artist widely regarded as one of the greatest heavyweight fighters in the sport’s history.
  • D. Kenny Florian
    Kenny Florian is a retired American mixed martial artist and longtime UFC lightweight contender who later became a prominent MMA analyst and commentator.
  • E. Andrew Golota
    Andrew Golota is a Polish former professional heavyweight boxer best known for his controversial fights, including multiple disqualifications and high-profile bouts in the 1990s and early 2000s.
  • 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_69d87f221d8081909b0b2063e7528ba2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e245c4a0b08190af3574f087205afc completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a001f8ca4508190a8ed7a9159dfb551 completed May 10, 2026, 6:02 a.m.
Created at: April 10, 2026, 5:04 a.m.