Triple

T37673049
Position Surface form Disambiguated ID Type / Status
Subject Volga–Kama river system E938013 entity
Predicate containsConfluence P3421 FINISHED
Object confluence of Volga and Kama rivers — LITERAL 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: confluence of Volga and Kama rivers | Statement: [Volga–Kama river system, containsConfluence, confluence of Volga and Kama rivers]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: containsConfluence
Context triple: [Volga–Kama river system, containsConfluence, confluence of Volga and Kama rivers]
  • A. confluenceWith
    Indicates that one entity joins or merges together with another, typically at a shared meeting point.
  • B. confluenceLocation chosen
    Indicates the place where two or more flowing entities (such as rivers or streams) meet and merge.
  • C. startsAfterConfluenceOf
    Indicates that one entity begins at a point located downstream from, and subsequent to, the confluence where two or more other entities merge.
  • D. confluenceCharacteristic
    Indicates a characteristic or property that specifically pertains to the confluence or merging point of two or more entities.
  • E. hasMajorConfluence
    Indicates that a watercourse joins with another watercourse at a significant or primary confluence point.
  • F. None of above.

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_69f76ed7b1408190ba8c93c53cb8becf completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_6a01c41dfe248190a68f4a262591b30f completed May 11, 2026, 11:57 a.m.
PD Predicate disambiguation batch_6a01c375d14c8190a15bfa12623588a9 completed May 11, 2026, 11:54 a.m.
Created at: May 3, 2026, 4:18 p.m.