Triple

T4172747
Position Surface form Disambiguated ID Type / Status
Subject Stanislav Shushkevich E86401 entity
Predicate coSignedWith P9509 FINISHED
Object Leonid Kravchuk E74662 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: Leonid Kravchuk | Statement: [Stanislav Shushkevich, coSignedWith, Leonid Kravchuk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leonid Kravchuk
Context triple: [Stanislav Shushkevich, coSignedWith, Leonid Kravchuk]
  • A. Leonid Kravchuk chosen
    Leonid Kravchuk was the first President of independent Ukraine and a key political leader in the final stages of the Soviet Union’s collapse.
  • B. Yevhen Koshovyi
    Yevhen Koshovyi is a Ukrainian comedian and actor best known for his long-time work with the popular comedy troupe and TV show "Kvartal 95."
  • C. Vasyl Holoborodko
    Vasyl Holoborodko is the fictional history teacher who unexpectedly becomes president of Ukraine in the satirical Ukrainian TV series "Servant of the People," portrayed by Volodymyr Zelenskyy.
  • D. Mykola Azarov
    Mykola Azarov is a Ukrainian politician who served as Prime Minister of Ukraine and was a prominent figure in the pro-Russian Party of Regions.
  • E. Mykhailo Fedorov
    Mykhailo Fedorov is a Ukrainian politician and digital reformer known for leading the country’s ambitious e-government and digital transformation initiatives.
  • 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_69aed93de98c8190ad838ce507b77c8a completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af02e65b548190be095df62091b960 completed March 9, 2026, 5:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69b589f001e48190a4c5aab6cfd29ffb completed March 14, 2026, 4:16 p.m.
Created at: March 9, 2026, 3:45 p.m.