Triple

T20886982
Position Surface form Disambiguated ID Type / Status
Subject Hilda Múdra E514307 entity
Predicate student P7251 FINISHED
Object Ondrej Nepela 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: Ondrej Nepela | Statement: [Hilda Múdra, student, Ondrej Nepela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ondrej Nepela
Context triple: [Hilda Múdra, student, Ondrej Nepela]
  • A. Ondrej Nepela chosen
    Ondrej Nepela was a Slovak figure skater and 1972 Olympic champion, regarded as one of the most successful skaters of his era.
  • B. Nikolai Kulik
    Nikolai Kulik is a Russian mathematician known for his contributions to functional analysis and related areas of modern mathematics.
  • C. Grzegorz Kulik
    Grzegorz Kulik is a Silesian writer, translator, and activist known for promoting and translating literature into the Silesian language.
  • D. David Hackl
    David Hackl is a Canadian film director and production designer best known for his work on the Saw horror franchise, particularly directing Saw V.
  • E. Alexei Yagudin
    Alexei Yagudin is a Russian former competitive figure skater and Olympic champion known for his powerful jumping ability and charismatic performances.
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6d058d4dc81908398f8c75e30dc77 completed April 21, 2026, 1:18 a.m.
Created at: April 16, 2026, 12:46 p.m.