Triple

T19368325
Position Surface form Disambiguated ID Type / Status
Subject Obninsk E484463 entity
Predicate locatedOn P40 FINISHED
Object Protva River 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: Protva River | Statement: [Obninsk, locatedOn, Protva River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Protva River
Context triple: [Obninsk, locatedOn, Protva River]
  • A. Protva River chosen
    The Protva River is a river in western Russia that flows through the Moscow and Kaluga regions and is a tributary of the Oka River.
  • B. Svratka River
    The Svratka River is a significant river in the Czech Republic that flows through the city of Brno and helps shape the landscape of the South Moravian region.
  • C. Kriva River
    The Kriva River is a river in northeastern North Macedonia that flows near the town of Kriva Palanka and is a tributary of the Pčinja River.
  • D. Banovska River
    The Banovska River is a small river in southern Bulgaria that flows near the town of Dimitrovgrad.
  • E. Pliva River
    The Pliva River is a river in central Bosnia and Herzegovina known for its scenic waterfalls, lakes, and the historic town of Jajce along its course.
  • 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e619ae6838819080584d60cbd58bbd completed April 20, 2026, 12:18 p.m.
Created at: April 10, 2026, 1:35 p.m.