Triple

T11857329
Position Surface form Disambiguated ID Type / Status
Subject Uman–Botoșani offensive E282071 entity
Predicate capturedCity P8411 FINISHED
Object Uman E819910 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: Uman | Statement: [Uman–Botoșani offensive, capturedCity, Uman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uman
Context triple: [Uman–Botoșani offensive, capturedCity, Uman]
  • A. Uman chosen
    Uman is a historic city in central Ukraine known for its cultural heritage and the famous Sofiyivka Park.
  • B. Urum
    Urum is a Turkic language historically spoken by certain Greek communities, particularly in parts of Ukraine and the Caucasus.
  • C. Yuman
    Yuman is a Native American language family of the southwestern United States and northwestern Mexico, encompassing several related indigenous languages and peoples.
  • D. Gagra
    Gagra is a settlement located within Pakistan’s Buner District in the Khyber Pakhtunkhwa province.
  • E. Gagra
    Gagra is a coastal resort town on the Black Sea in the disputed region of Abkhazia, internationally recognized as part of Georgia.
  • 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_69d6ab287ba48190a5178779fd19b9b7 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a699089c8190b7a298baf13dcded completed April 10, 2026, 7:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69f2816404ac81909129347607fb5fd3 completed April 29, 2026, 10:08 p.m.
Created at: April 8, 2026, 9:43 p.m.