Triple

T16904719
Position Surface form Disambiguated ID Type / Status
Subject Tosno E424529 entity
Predicate locatedOn P40 FINISHED
Object Tosna 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: Tosna River | Statement: [Tosno, locatedOn, Tosna River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tosna River
Context triple: [Tosno, locatedOn, Tosna River]
  • A. Tosna River chosen
    The Tosna River is a waterway in northwestern Russia that flows through the Leningrad Oblast before joining the Neva River.
  • B. Oshmyanka River
    The Oshmyanka River is a waterway in eastern Europe that flows through the town of Oszmiana (Ashmyany) in present-day Belarus.
  • C. Belyayevo River
    The Belyayevo River is a small watercourse in the Moscow Oblast of Russia that flows through the town of Ramenskoye and forms part of its local natural landscape.
  • D. Yablon River
    The Yablon River is a significant watercourse in Russia’s Far East that feeds into the larger Anadyr River system.
  • E. Luga River
    The Luga River is a significant waterway in northwestern Russia that flows through Novgorod and Leningrad Oblasts before emptying into the Gulf of Finland in the Baltic Sea.
  • 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_69d889da3e8c8190a2b118f383f0beac completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3c8df454c8190898ebdd75985e51c completed April 18, 2026, 6:09 p.m.
Created at: April 10, 2026, 5:30 a.m.