Triple

T6213149
Position Surface form Disambiguated ID Type / Status
Subject Battle of Kherson E138918 entity
Predicate river P165 FINISHED
Object Dnipro River E41855 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: Dnipro River | Statement: [Battle of Kherson, river, Dnipro River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dnipro River
Context triple: [Battle of Kherson, river, Dnipro River]
  • A. Kharkiv River
    The Kharkiv River is a waterway in northeastern Ukraine that flows through and lends its name to the city of Kharkiv before joining the Lopan River.
  • B. Dnieper chosen
    The Dnieper is a major Eastern European river that flows through Russia, Belarus, and Ukraine before emptying into the Black Sea.
  • C. Taras River
    The Taras River is an ancient waterway in southern Italy historically associated with the Greek colony of Tarentum (modern Taranto) on the Ionian Sea.
  • D. Vorskla River
    The Vorskla River is a significant tributary of the Dnieper River in central Ukraine, known for its historical battle sites and role in regional ecology and transport.
  • E. Trubizh River
    The Trubizh River is a tributary of the Dnieper in central Ukraine, flowing through the historic town of Pereiaslav and the surrounding Kyiv region.
  • 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_69c008ada364819096c9e92c74d639b5 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0628c52ec8190b9c62c7fdc0aa83b completed March 22, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20da55e3c81909a61471b38e88894 completed March 24, 2026, 4:05 a.m.
Created at: March 22, 2026, 4:21 p.m.