Triple

T19156295
Position Surface form Disambiguated ID Type / Status
Subject Lypky E468934 entity
Predicate partOf P40 FINISHED
Object Pechersk 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: Pechersk | Statement: [Lypky, partOf, Pechersk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pechersk
Context triple: [Lypky, partOf, Pechersk]
  • A. Pechersky
    Pechersky is a surname most notably associated with Alexander Pechersky, a leader of the 1943 Sobibor extermination camp uprising during the Holocaust.
  • B. Pecherska chosen
    Pecherska is a Kyiv Metro station on the Syretsko–Pecherska line serving the Pechersk district of Ukraine’s capital.
  • C. Usvyaty
    Usvyaty is an urban-type settlement in Pskov Oblast, Russia, known as a local administrative and cultural center near the borders with Belarus and Latvia.
  • D. Sviatoshyn
    Sviatoshyn is a residential neighborhood in Kyiv, Ukraine, known for its location along the city’s metro system and its mix of Soviet-era housing and green spaces.
  • E. Kievskaya
    Kievskaya is a prominent Moscow Metro station complex known for its ornate, Ukrainian-themed architecture and role as a major transfer hub.
  • 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5eeb9cf9081908b17073755e83554 completed April 20, 2026, 9:15 a.m.
Created at: April 10, 2026, 12:06 p.m.