Triple

T21565456
Position Surface form Disambiguated ID Type / Status
Subject Бесы E532150 entity
Predicate mainCharacter P1183 FINISHED
Object Кириллов 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: Кириллов | Statement: [Бесы, mainCharacter, Кириллов]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Кириллов
Context triple: [Бесы, mainCharacter, Кириллов]
  • A. Kirilov chosen
    Kirilov is a philosophical and tormented character in Fyodor Dostoevsky’s novel "Demons," known for his radical ideas about freedom, God, and suicide.
  • B. Kirillovich
    Kirillovich is the Russian patronymic of Pierre Bezukhov, indicating he is the son of a man named Kirill.
  • C. Grigory Spiridov
    Grigory Spiridov was a prominent 18th-century Russian admiral best known for his leadership in the Russo-Turkish War, particularly at the Battle of Chesma.
  • D. Vasily Kosyakov
    Vasily Kosyakov was a prominent Russian architect known for his influential work in the Russian Revival style, particularly in religious and monumental architecture.
  • E. Konstantin Vasilyev
    Konstantin Vasilyev was an actor known for his role in Sergei Eisenstein’s 1929 Soviet silent film "The General Line" (also known as "Old and New").
  • 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_69e0c460db088190828c64206a450273 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eed2e777c881908de84493fa939ff3 completed April 27, 2026, 3:07 a.m.
Created at: April 16, 2026, 6:30 p.m.