Triple

T8270973
Position Surface form Disambiguated ID Type / Status
Subject Stars on Ice E193425 entity
Predicate performer P1363 FINISHED
Object Ekaterina Gordeeva E197963 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: Ekaterina Gordeeva | Statement: [Stars on Ice, performer, Ekaterina Gordeeva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ekaterina Gordeeva
Context triple: [Stars on Ice, performer, Ekaterina Gordeeva]
  • A. Ekaterina Gordeeva chosen
    Ekaterina Gordeeva is a Russian former pair skater and two-time Olympic champion, renowned for her artistry and partnership with the late Sergei Grinkov.
  • B. Oksana Grishuk
    Oksana Grishuk is a Russian former ice dancer best known as a multiple-time Olympic and World champion with partner Evgeni Platov.
  • C. Tatiana Tarasova
    Tatiana Tarasova is a renowned Russian figure skating coach and choreographer known for guiding numerous skaters to Olympic and World Championship titles.
  • D. Darya Domracheva
    Darya Domracheva is a Belarusian former biathlete and multiple Olympic champion renowned as one of the most successful female athletes in the sport’s history.
  • E. Elena Berezhnaya
    Elena Berezhnaya is a Russian former pair skater best known for her successful partnership with Anton Sikharulidze, with whom she won multiple World and Olympic medals.
  • 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_69ca82e14ae481908ffdb822cd2192bc completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7986f8cc8190a529dda980dd6e98 completed March 31, 2026, 7:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde75a2e048190b0de47a21e662baa completed April 2, 2026, 3:49 a.m.
Created at: March 30, 2026, 5:50 p.m.