Triple

T20076985
Position Surface form Disambiguated ID Type / Status
Subject My Sister's Keeper E499892 entity
Predicate stars P1956 FINISHED
Object Sofia Vassilieva 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: Sofia Vassilieva | Statement: [My Sister's Keeper, stars, Sofia Vassilieva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sofia Vassilieva
Context triple: [My Sister's Keeper, stars, Sofia Vassilieva]
  • A. Sofia Vassilieva chosen
    Sofia Vassilieva is an American actress best known for her roles in the TV series "Medium" and the film "My Sister's Keeper."
  • B. Viktoria Timofeyeva
    Viktoria Timofeyeva is a Russian artist known for her collaborative work and partnership with her late husband, muralist Dmitri Vrubel, including contributions to politically charged public art.
  • C. Viktoriya Isakova
    Viktoriya Isakova is a Russian film, television, and theater actress known for her versatile dramatic roles in contemporary Russian cinema and TV series.
  • D. Ekaterina Peshkova
    Ekaterina Peshkova was a Russian human rights activist and the first wife of writer Maxim Gorky, known for her work in political prisoner aid and civil rights advocacy in early Soviet Russia.
  • E. Mariya Timofeyeva
    Mariya Timofeyeva was a Soviet film editor best known for her work on classic films such as the 1959 war drama "Ballad of a Soldier."
  • 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6643d5238819098b7d4e4e2c8dd67 completed April 20, 2026, 5:37 p.m.
Created at: April 11, 2026, 3:40 p.m.