Triple

T17097821
Position Surface form Disambiguated ID Type / Status
Subject Belorussian strategic offensive operation E414893 entity
Predicate capturedCity P8411 FINISHED
Object Orsha E215208 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: Orsha | Statement: [Belorussian strategic offensive operation, capturedCity, Orsha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orsha
Context triple: [Belorussian strategic offensive operation, capturedCity, Orsha]
  • A. Orsha chosen
    Orsha is a historic city in eastern Belarus known as a regional transport hub and site of several significant battles.
  • B. Moghiliov-Podolsk
    Moghiliov-Podolsk is the Romanian name for Mogilev-Podilskyi, a city in western Ukraine located on the Dniester River near the border with Moldova.
  • C. Borisoglebsk
    Borisoglebsk is a small Russian city known for its historical architecture and location on the Vorona River in southwestern Russia.
  • D. Kozelsk
    Kozelsk is a historic town in western Russia known for its medieval defenses and location within Kaluga Oblast.
  • E. Vitebsk
    Vitebsk is a historic city in northeastern Belarus known as a major cultural center and the birthplace of artist Marc Chagall.
  • 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_69d886cfc8e88190b05ba466edd35591 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbffafb08190baf9e0b4fdf1b404 completed April 18, 2026, 7:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012eefd5f08190b9eb8a81e45a9921 completed May 11, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:35 a.m.