Triple

T20657606
Position Surface form Disambiguated ID Type / Status
Subject Little Usutu River E507667 entity
Predicate hasName P744 FINISHED
Object Little Usutu 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: Little Usutu River | Statement: [Little Usutu River, hasName, Little Usutu River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Little Usutu River
Context triple: [Little Usutu River, hasName, Little Usutu River]
  • A. Little Usutu River chosen
    The Little Usutu River is a smaller watercourse in southern Africa that feeds into the larger Great Usutu River system.
  • B. Minija River
    The Minija River is a waterway in western Lithuania that flows through the Samogitia region before emptying into the Curonian Lagoon near the Baltic Sea.
  • C. Ulla River
    Ulla River is a tributary watercourse in Eastern Europe that feeds into the larger Daugava River system.
  • D. Tinkisso River
    The Tinkisso River is a significant waterway in West Africa that flows through Guinea and contributes to the Niger River basin.
  • E. Omulew River
    The Omulew River is a tributary watercourse in northeastern Poland that feeds into the larger Narew River system.
  • 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_69e0b4bf58c081908e52a4500e03ff83 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b2ee049081909904efe2dc683cd5 completed April 20, 2026, 11:12 p.m.
Created at: April 16, 2026, 11:43 a.m.