Triple

T11352795
Position Surface form Disambiguated ID Type / Status
Subject Sydir Kovpak E268875 entity
Predicate name P16 FINISHED
Object Sydir Kovpak E268875 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: Sydir Kovpak | Statement: [Sydir Kovpak, name, Sydir Kovpak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sydir Kovpak
Context triple: [Sydir Kovpak, name, Sydir Kovpak]
  • A. Sydir Kovpak chosen
    Sydir Kovpak was a prominent Soviet Ukrainian partisan leader and twice Hero of the Soviet Union known for organizing large-scale guerrilla operations against Nazi forces during World War II.
  • B. Sviatoslav Shevchuk
    Sviatoslav Shevchuk is the head of the Ukrainian Greek Catholic Church and a prominent Ukrainian church leader known for his pastoral work and advocacy for his country.
  • C. Andriy Franko
    Andriy Franko was the son of prominent Ukrainian writer and political activist Ivan Franko.
  • D. Taras Prodaniuk
    Taras Prodaniuk is an American bassist and session musician known for his work in country and roots rock, including collaborations with artists like Dwight Yoakam.
  • E. Oleksandr Turchynov
    Oleksandr Turchynov is a Ukrainian politician and former acting president who played a key role during the 2014 political transition following the Euromaidan protests.
  • 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_69d6aacbe18081909e5fadb50082dd96 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea24489081908fbf47fd2e6d709c completed April 9, 2026, 6:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69e543a6e97481909dc77a553b217b4d completed April 19, 2026, 9:05 p.m.
Created at: April 8, 2026, 9:33 p.m.