Triple

T13947351
Position Surface form Disambiguated ID Type / Status
Subject Letters from Exile E335422 entity
Predicate author P4 FINISHED
Object Natalia Sedova E66864 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: Natalia Sedova | Statement: [Letters from Exile, author, Natalia Sedova]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Natalia Sedova
Context triple: [Letters from Exile, author, Natalia Sedova]
  • A. Natalia Sedova chosen
    Natalia Sedova was a Russian revolutionary, Marxist activist, and intellectual best known as the lifelong partner and political collaborator of Leon Trotsky.
  • B. Natalya Ivanova
    Natalya Ivanova is a film producer known for her work on the movie "Two Women."
  • C. Elena Kurakina
    Elena Kurakina was a Russian noblewoman of the influential Kurakin family, connected by birth to the prominent Dolgorukov princely line.
  • D. Natalya Simonova
    Natalya Simonova is a Russian computer programmer and Bond girl who serves as the primary female lead and ally to James Bond in the 1995 film "GoldenEye."
  • E. Anya Amasova
    Anya Amasova is a Soviet KGB agent and Bond girl featured in the James Bond film "The Spy Who Loved Me."
  • 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_69d81c6081b88190b53e317c3370c8fe completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e12171c8190b95746bdd4845def completed April 14, 2026, 12:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac89ebd48190ab448f74daf82a96 completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:17 p.m.