Triple

T20255451
Position Surface form Disambiguated ID Type / Status
Subject Koko E498682 entity
Predicate trainer P41095 FINISHED
Object Nelson Woss 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: Nelson Woss | Statement: [Koko, trainer, Nelson Woss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nelson Woss
Context triple: [Koko, trainer, Nelson Woss]
  • A. Nelson Woss chosen
    Nelson Woss is an Australian film producer best known for his work on the popular family film "Red Dog" and its related projects.
  • B. Nelson McDowell
    Nelson McDowell was an American character actor of the silent and early sound film era, known for his distinctive gaunt appearance and frequent roles in Westerns and serials.
  • C. Walter Nelson
    Walter Nelson was an attorney who served on the defense team in the landmark Ossian Sweet murder trial, which challenged racial injustice in 1920s Detroit.
  • D. Nelson Emerson
    Nelson Emerson is a Canadian former professional ice hockey forward who played over a decade in the NHL for multiple teams and later became an executive and development coach.
  • E. John Nelson
    John Nelson is a central fictional figure in the Western-themed narrative of "Kansas Pacific," around whom much of the story's action and conflict revolves.
  • 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_69da6275fa6c8190952924930adee150 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e673ab60388190be32cc69bf2b6f76 completed April 20, 2026, 6:42 p.m.
Created at: April 11, 2026, 11:41 p.m.