Triple

T22036207
Position Surface form Disambiguated ID Type / Status
Subject Kozelets E544214 entity
Predicate region P40 FINISHED
Object Chernihiv region 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: Chernihiv region | Statement: [Kozelets, region, Chernihiv region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chernihiv region
Context triple: [Kozelets, region, Chernihiv region]
  • A. Chernihiv region chosen
    Chernihiv region is a historic and administrative area in northern Ukraine, known for its ancient cities, cultural heritage, and strategic location near the borders with Belarus and Russia.
  • B. Kyiv Oblast
    Kyiv Oblast is a central administrative region of Ukraine surrounding, but administratively separate from, the nation’s capital city of Kyiv.
  • C. Rivne Oblast
    Rivne Oblast is an administrative region in northwestern Ukraine known for its mixed agricultural and industrial economy, forests and river landscapes, and historical sites dating back to medieval times.
  • D. Voroshylovhrad Oblast
    Voroshylovhrad Oblast was the Soviet-era name of the administrative region in eastern Ukraine now known as Luhansk Oblast.
  • E. Zhytomyr Oblast
    Zhytomyr Oblast is an administrative region in northern-central Ukraine known for its mixed forests, agricultural lands, and historical cities such as Zhytomyr.
  • 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_69e11e2f98c8819083e11eab90942a78 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127f1f95c8190a324c84313cd91ee completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:25 p.m.