Triple

T21134804
Position Surface form Disambiguated ID Type / Status
Subject Donald "Red" Grant E520788 entity
Predicate appearsAlongside P25756 FINISHED
Object Tatiana Romanova 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: Tatiana Romanova | Statement: [Donald "Red" Grant, appearsAlongside, Tatiana Romanova]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tatiana Romanova
Context triple: [Donald "Red" Grant, appearsAlongside, Tatiana Romanova]
  • A. Tatiana Romanova chosen
    Tatiana Romanova is a Soviet cipher clerk and key Bond girl who becomes entangled with James Bond in the espionage plot of Ian Fleming’s novel and its film adaptation "From Russia with Love."
  • B. Natalia Sedova
    Natalia Sedova was a Russian revolutionary, Marxist activist, and intellectual best known as the lifelong partner and political collaborator of Leon Trotsky.
  • C. Natalya Ivanova
    Natalya Ivanova is a film producer known for her work on the movie "Two Women."
  • D. Anastasia Markovna
    Anastasia Markovna was the wife of the 17th-century Russian Old Believer leader and writer Protopope Avvakum, remembered for her steadfast support during his religious persecution.
  • E. Natasha
    Natasha is a song by the South Korean girl group Wanna One, featured as part of their musical releases.
  • 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_69e0b50b53048190ae34e8abbe3c5ada completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e723592fd48190ba5977a1b229d51e completed April 21, 2026, 7:12 a.m.
Created at: April 16, 2026, 2:56 p.m.