Triple

T19866755
Position Surface form Disambiguated ID Type / Status
Subject Battle of Donbas (2022) E477410 entity
Predicate frontlineCity P3207 FINISHED
Object Kramatorsk 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: Kramatorsk | Statement: [Battle of Donbas (2022), frontlineCity, Kramatorsk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kramatorsk
Context triple: [Battle of Donbas (2022), frontlineCity, Kramatorsk]
  • A. Kramatorsk chosen
    Kramatorsk is an industrial city in eastern Ukraine that has become a key administrative and strategic center in the Donbas region.
  • B. Kremenchuk
    Kremenchuk is an industrial city in central Ukraine on the Dnieper River, historically significant as a major transport and strategic hub.
  • C. Voznesensk
    Voznesensk is a city in southern Ukraine known as an industrial and transport center situated on the Southern Bug River.
  • D. Melitopol
    Melitopol is a strategically important industrial and transportation hub in southeastern Ukraine, known for its agricultural production and key road and rail connections.
  • E. Kupiansk
    Kupiansk is a strategically important city in Ukraine’s Kharkiv Oblast, serving as a key railway and logistics hub near the front lines of the Russo-Ukrainian War.
  • 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_69d8e51e7d948190aedbcd6c30361c39 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6589f9654819080597a4f7c52d64c completed April 20, 2026, 4:47 p.m.
Created at: April 10, 2026, 1:51 p.m.