Triple

T10445825
Position Surface form Disambiguated ID Type / Status
Subject Viktor Drago E246283 entity
Predicate mother P120 FINISHED
Object Ludmilla Drago E342117 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: Ludmilla Drago | Statement: [Viktor Drago, mother, Ludmilla Drago]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ludmilla Drago
Context triple: [Viktor Drago, mother, Ludmilla Drago]
  • A. Ludmilla Drago chosen
    Ludmilla Drago is a supporting character in the film "Rocky IV," known as the confident and nationalistic wife and spokesperson of Soviet boxer Ivan Drago.
  • B. Tatyana Lioznova
    Tatyana Lioznova was a Soviet film and television director best known for her influential spy drama works and contributions to Russian cinema.
  • C. Ludmilla
    Ludmilla is a coastal suburb of Darwin in Australia's Northern Territory, known for its residential areas and proximity to Fannie Bay.
  • D. Valentina Yankovskaya
    Valentina Yankovskaya is a Soviet film editor best known for her work on the classic comedy "The Diamond Arm."
  • E. Lilia Podkopayeva
    Lilia Podkopayeva is a Ukrainian artistic gymnast and 1996 Olympic all-around champion renowned for her elegant style and highly difficult routines.
  • 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4fdbf81508190a160edea85105d3a completed April 7, 2026, 12:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4f31e3d5c8190a044eaf67ebc9f08 completed April 19, 2026, 3:22 p.m.
Created at: April 6, 2026, 12:16 p.m.