Triple

T87001
Position Surface form Disambiguated ID Type / Status
Subject Kato Svanidze E1749 entity
Predicate familyName P18 FINISHED
Object Svanidze E1749 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: Svanidze | Statement: [Kato Svanidze, familyName, Svanidze]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Svanidze
Context triple: [Kato Svanidze, familyName, Svanidze]
  • A. Kato Svanidze chosen
    Kato Svanidze was the first wife of Joseph Stalin, remembered primarily for her early death and its profound emotional impact on him.
  • B. Ivan Susloparov
    Ivan Susloparov was a Soviet general and military diplomat who represented the USSR at the signing of Germany’s unconditional surrender in World War II.
  • C. Gori
    Gori is a city in central Georgia best known as the birthplace of Soviet leader Joseph Stalin.
  • D. Andrei
    Andrei is a masculine given name commonly used in Slavic and Eastern European countries, equivalent to the English name Andrew.
  • E. Abkhazians
    Abkhazians are a Northwest Caucasian ethnic group primarily inhabiting the region of Abkhazia on the eastern coast of the Black Sea, with their own distinct language, culture, and historical identity.
  • 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_69a24c8150408190910a693eb51c1f71 completed Feb. 28, 2026, 2:01 a.m.
NER Named-entity recognition batch_69a24f50e004819083f5bfccd597a312 completed Feb. 28, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2a3d094608190929dd69b14755976 completed Feb. 28, 2026, 8:14 a.m.
Created at: Feb. 28, 2026, 2:06 a.m.