Triple

T17855901
Position Surface form Disambiguated ID Type / Status
Subject Siva River E445935 entity
Predicate mouth P407 FINISHED
Object Kama 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: Kama River | Statement: [Siva River, mouth, Kama River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kama River
Context triple: [Siva River, mouth, Kama River]
  • A. Kama River chosen
    The Kama River is a major waterway in western Russia that serves as one of the largest and most significant tributaries of the Volga River.
  • B. Kunene River
    The Kunene River is a major river in southwestern Africa that forms part of the border between Angola and Namibia and is known for features like the Epupa Falls.
  • C. Tembe River
    The Tembe River is a watercourse in southern Mozambique that flows into Maputo Bay, contributing to the bay’s estuarine system.
  • D. Lek River
    The Lek River is a major distributary branch of the Rhine in the Netherlands, playing an important role in the country’s inland waterway network and flood management system.
  • E. Great Kwa River
    The Great Kwa River is a significant waterway in southeastern Nigeria known for its rich biodiversity and role in supporting local communities and ecosystems.
  • 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_69d8b9f26f18819089c9e43250bee6ae completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4978bd5e081909e192f6aada5235f completed April 19, 2026, 8:51 a.m.
Created at: April 10, 2026, 10:17 a.m.