Triple

T23280766
Position Surface form Disambiguated ID Type / Status
Subject Sofya Tolstaya E588853 entity
Predicate patronymicName P7966 FINISHED
Object Andreyevna 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: Andreyevna | Statement: [Sofya Tolstaya, patronymicName, Andreyevna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andreyevna
Context triple: [Sofya Tolstaya, patronymicName, Andreyevna]
  • A. Andreyevna chosen
    Andreyevna is a Russian patronymic indicating that a woman is the daughter of a man named Andrey.
  • B. Vasilyevna
    Vasilyevna is a Russian female patronymic name indicating that the person's father is named Vasily.
  • C. Antonovna
    Antonovna is a Russian patronymic name derived from the male given name Anton, indicating "child of Anton."
  • D. Ermolaeva
    Ermolaeva is a Russian surname most notably associated with figures such as the avant-garde artist and illustrator Vera Ermolaeva.
  • E. Praskovya Fyodorovna
    Praskovya Fyodorovna is the self-absorbed and socially preoccupied wife of the dying judge in Leo Tolstoy’s novella "The Death of Ivan Ilyich," embodying the superficiality and moral emptiness of the society around him.
  • 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_69e25d16e2c08190a291de254703129e completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f19642b46481909fd455acd2155792 completed April 29, 2026, 5:25 a.m.
Created at: April 17, 2026, 4:56 p.m.