Triple

T20155888
Position Surface form Disambiguated ID Type / Status
Subject Kegalle District E491563 entity
Predicate hasRiver P165 FINISHED
Object Kelani 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: Kelani River | Statement: [Kegalle District, hasRiver, Kelani River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelani River
Context triple: [Kegalle District, hasRiver, Kelani River]
  • A. Kelani River chosen
    The Kelani River is one of Sri Lanka’s major rivers, flowing from the central highlands through key urban areas including Colombo before emptying into the Indian Ocean.
  • B. Belham River
    Belham River is a seasonal river on the Caribbean island of Montserrat, known for carrying volcanic ash and debris from the Soufrière Hills volcano through the Belham Valley to the sea.
  • C. Tuivawl River
    Tuivawl River is a river in the northeastern Indian state of Mizoram that flows through the Mizo Hills region.
  • D. Ofiki River
    The Ofiki River is a significant waterway in southwestern Nigeria that serves as a major tributary contributing to the flow of the Ogun River.
  • E. Meriti River
    The Meriti River is a watercourse in the state of Rio de Janeiro, Brazil, that flows through the metropolitan area and empties into Guanabara Bay.
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667e0a0488190a25d92aaf300be4a completed April 20, 2026, 5:52 p.m.
Created at: April 11, 2026, 11:34 p.m.