Triple

T4483118
Position Surface form Disambiguated ID Type / Status
Subject Bill Viola E100176 entity
Predicate collaborator P11349 FINISHED
Object Kira Perov E443985 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: Kira Perov | Statement: [Bill Viola, collaborator, Kira Perov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kira Perov
Context triple: [Bill Viola, collaborator, Kira Perov]
  • A. Kira Perov chosen
    Kira Perov is an Australian-born curator and executive director of the Bill Viola Studio, known for her long-term creative collaboration with video artist Bill Viola in producing and presenting his work worldwide.
  • B. Irina Korina
    Irina Korina is the mother of late Russian-American actor Anton Yelchin.
  • C. Ekaterina Maximova
    Ekaterina Maximova was a celebrated Soviet and Russian ballerina renowned for her lyrical artistry and long-standing career as a principal dancer with the Bolshoi Ballet.
  • D. Katja Koroleva
    Katja Koroleva is an American soccer referee known for officiating at the highest levels of women’s professional and international football.
  • E. Elena Karam
    Elena Karam is an actress known for her role in Elia Kazan’s 1963 drama film "America America."
  • 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_69b34553cbe48190afa8ac1cac285b86 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b356fd35088190be79efc6c7317e2a completed March 13, 2026, 12:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69b65140f9a08190856442534ff46e37 completed March 15, 2026, 6:27 a.m.
Created at: March 12, 2026, 11:36 p.m.