Triple

T23178565
Position Surface form Disambiguated ID Type / Status
Subject Masha Prozorova E579083 entity
Predicate givenName P17 FINISHED
Object Masha 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: Masha | Statement: [Masha Prozorova, givenName, Masha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Masha
Context triple: [Masha Prozorova, givenName, Masha]
  • A. Masha
    Masha is a town in southwestern Ethiopia that serves as an administrative and commercial center in the Sheka Zone.
  • B. Masha chosen
    Masha is a diminutive and affectionate Russian form of the given name Mary (Maria).
  • C. Marichka
    Marichka is a key supporting character in the dystopian film "Children of Men," known for helping protect the first pregnant woman in years.
  • D. Mishka
    Mishka is a reggae-influenced singer-songwriter known for his mellow, island-inspired sound and collaborations within the jam and surf music scenes.
  • E. Mashenka
    Mashenka is a Russian diminutive form of the female given name Maria, often used affectionately for girls and women.
  • 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_69e245fd2a388190b814c0dfa15f7148 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18f6cbe5481909444479b7eac47f7 completed April 29, 2026, 4:56 a.m.
Created at: April 17, 2026, 4:04 p.m.