Triple

T22588759
Position Surface form Disambiguated ID Type / Status
Subject Préfontaine E564876 entity
Predicate hasVariant P455 FINISHED
Object Prefontaine 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: Prefontaine | Statement: [Préfontaine, hasVariant, Prefontaine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prefontaine
Context triple: [Préfontaine, hasVariant, Prefontaine]
  • A. Steve Prefontaine chosen
    Steve Prefontaine was a legendary American middle- and long-distance runner whose aggressive racing style and record-setting performances at the University of Oregon made him an icon of track and field in the early 1970s.
  • B. Bowerman
    Bowerman is a surname most prominently associated with Bill Bowerman, the legendary American track coach and co-founder of Nike.
  • C. Frank Shorter
    Frank Shorter is an American long-distance runner best known for winning the marathon gold medal at the 1972 Munich Olympics and helping spark the running boom in the United States.
  • D. Eric Liddell
    Eric Liddell was a Scottish sprinter and Christian missionary best known for winning the 400 metres gold medal at the 1924 Paris Olympics and for his principled refusal to run on Sunday.
  • E. Bobby Hayes
    Bobby Hayes is a character in the supernatural action-comedy film "R.I.P.D.," which follows deceased law enforcement officers policing rogue spirits in the afterlife.
  • 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_69e245836014819091b91ed3074742a3 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1615ea5bc8190b7760cd0de9669dd completed April 29, 2026, 1:39 a.m.
Created at: April 17, 2026, 2:48 p.m.