Triple

T2640452
Position Surface form Disambiguated ID Type / Status
Subject Matabeleland E62851 entity
Predicate borderFeature P1896 FINISHED
Object Shashe River E116368 NE 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: Shashe River | Statement: [Matabeleland, borderFeature, Shashe River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shashe River
Context triple: [Matabeleland, borderFeature, Shashe River]
  • A. Shashe River chosen
    The Shashe River is a significant watercourse in southern Africa that flows through Botswana and Zimbabwe before joining the Limpopo River.
  • B. Adhaim River
    The Adhaim River is a significant river in Iraq that flows through the northeastern part of the country before joining the Tigris.
  • C. Sonai River
    The Sonai River is a tributary waterway in northeastern India that feeds into the larger Barak River system.
  • D. Rukni River
    The Rukni River is a lesser-known tributary stream that feeds into the larger Barak River system in northeastern India.
  • E. Nyamiha River
    The Nyamiha River is a small, historically significant waterway in Minsk, Belarus, now largely confined to underground culverts beneath the city.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ab4c3f2dcc819082df80f5e032f690 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abd8fc8ee881908a9f6820d8934a62 completed March 7, 2026, 7:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69be4d59f188819093e3a6c7037593cf completed March 21, 2026, 7:48 a.m.
Created at: March 6, 2026, 9:53 p.m.