Triple

T9046005
Position Surface form Disambiguated ID Type / Status
Subject Stalker E216756 entity
Predicate producer P490 FINISHED
Object Aleksandra Demidova E783115 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: Aleksandra Demidova | Statement: [Stalker, producer, Aleksandra Demidova]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aleksandra Demidova
Context triple: [Stalker, producer, Aleksandra Demidova]
  • A. Aleksandra Demidova chosen
    Aleksandra Demidova is a Soviet film producer best known for her work on Andrei Tarkovsky’s acclaimed science fiction film "Stalker" (1979).
  • B. Alexandra Velyaminova
    Alexandra Velyaminova was a Russian noblewoman of the 14th century, best known as the mother of Grand Prince Dmitry Donskoy of Moscow.
  • C. Natalia Staritskaya
    Natalia Staritskaya was the wife of prominent Russian and Soviet scientist Vladimir Vernadsky, known for her role in his personal and family life.
  • D. Daria Grinkova
    Daria Grinkova is the daughter of Russian Olympic champion figure skaters Ekaterina Gordeeva and the late Sergei Grinkov.
  • E. Natalia Bestemianova
    Natalia Bestemianova is a former Soviet ice dancer and Olympic champion renowned for her dramatic, expressive style and multiple World and European titles with partner Andrei Bukin.
  • 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_69ca83d22d488190adbce5e020e9cd1d completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc6b4e4b888190a425e29b193b506f completed April 1, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d369226a28819088b14cbc4cb78e57 completed April 6, 2026, 8:04 a.m.
Created at: March 30, 2026, 7:09 p.m.