Triple

T12788355
Position Surface form Disambiguated ID Type / Status
Subject Protivín E305690 entity
Predicate locatedOnRiver P165 FINISHED
Object Blanice 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: Blanice River | Statement: [Protivín, locatedOnRiver, Blanice River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blanice River
Context triple: [Protivín, locatedOnRiver, Blanice River]
  • A. Blanice River chosen
    The Blanice River is a river in the Czech Republic that flows through the town of Vlašim and forms part of the Sázava River basin.
  • B. Prądnik River
    The Prądnik River is a small river in southern Poland known for carving the picturesque limestone valley that runs through Ojców and the surrounding Ojców National Park.
  • C. Wieprz River
    The Wieprz River is a major river in eastern Poland that flows through the Lublin region before joining the Vistula River.
  • D. Glazne River
    The Glazne River is a mountain river in southwestern Bulgaria that flows through the town of Bansko in the Pirin region.
  • E. Radbuza River
    The Radbuza River is a river in the Czech Republic that flows through the Plzeň Region and contributes to the formation of the Berounka River.
  • 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_69d7bdf366888190a8cccb982606889c completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e6a61f48190972e241e70bc392c completed April 10, 2026, 9:40 p.m.
Created at: April 9, 2026, 5:30 p.m.