Triple

T21164662
Position Surface form Disambiguated ID Type / Status
Subject Nossob River E521527 entity
Predicate locatedIn P40 FINISHED
Object Kalahari Desert 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: Kalahari Desert | Statement: [Nossob River, locatedIn, Kalahari Desert]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kalahari Desert
Context triple: [Nossob River, locatedIn, Kalahari Desert]
  • A. Kalahari Desert chosen
    The Kalahari Desert is a vast semi-arid sandy savanna in southern Africa known for its red dunes, sparse vegetation, and unique wildlife adapted to its dry conditions.
  • B. Namib Desert
    The Namib Desert is a vast, ancient coastal desert in southwestern Africa, renowned for its towering red sand dunes and extreme arid conditions along the Atlantic coast.
  • C. Kalahari Basin
    The Kalahari Basin is a large inland drainage basin in southern Africa that encompasses and gives rise to the arid Kalahari Desert and surrounding semi-arid regions.
  • D. Bayuda Desert
    The Bayuda Desert is an arid, sparsely populated desert region in northern Sudan, bounded by a great bend of the Nile and known for its harsh terrain and historical caravan and military routes.
  • E. Muyunkum Desert
    The Muyunkum Desert is an arid desert region in southern Kazakhstan characterized by sandy plains and sparse vegetation.
  • 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_69e0b50e30748190b186824a206d39b9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7270e15bc81908d609198e573040e completed April 21, 2026, 7:28 a.m.
Created at: April 16, 2026, 2:59 p.m.