Triple

T22985747
Position Surface form Disambiguated ID Type / Status
Subject Edward Cheserek E571600 entity
Predicate nickname P55 FINISHED
Object King Cheserek 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: King Cheserek | Statement: [Edward Cheserek, nickname, King Cheserek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: King Cheserek
Context triple: [Edward Cheserek, nickname, King Cheserek]
  • A. Edward Cheserek chosen
    Edward Cheserek is a Kenyan-born middle- and long-distance runner who became one of the most decorated athletes in NCAA history while competing for the University of Oregon.
  • B. Ben Mize
    Ben Mize is an American drummer best known for his work with the rock band Counting Crows during the 1990s and early 2000s.
  • C. Dean Locke
    Dean Locke was an early settler and prominent local figure after whom the town of Lockeford, California, was named.
  • D. A. C. Lyles
    A. C. Lyles was an American film producer best known for his long association with Paramount Pictures and for producing a series of low-budget Westerns in the 1950s and 1960s.
  • E. Marlon Ross
    Marlon Ross is a distinguished American scholar and literary critic known for his work on race, gender, and sexuality in 19th- and 20th-century literature and culture.
  • 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_69e245b3c50481908bb3741ec9f40862 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f182996ee08190ab74014ee7ecac2b completed April 29, 2026, 4:01 a.m.
Created at: April 17, 2026, 3:49 p.m.