Triple

T1079123
Position Surface form Disambiguated ID Type / Status
Subject ǀXam E23906 entity
Predicate region P40 FINISHED
Object Upper Karoo E73016 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: Upper Karoo | Statement: [ǀXam, region, Upper Karoo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Upper Karoo
Context triple: [ǀXam, region, Upper Karoo]
  • A. Karoo chosen
    The Karoo is a vast semi-arid region in South Africa characterized by sparse vegetation, unique succulent flora, and extreme temperature variations.
  • B. Highveld
    The Highveld is a high-altitude grassland plateau in central South Africa known for its extensive farming, mining, and major cities such as Johannesburg and Pretoria.
  • C. Namaqualand
    Namaqualand is a semi-desert region in southwestern Africa famed for its spectacular seasonal wildflower displays and unique biodiversity.
  • D. Baviaanskloof Wilderness Area
    Baviaanskloof Wilderness Area is a rugged, biodiverse protected region in South Africa renowned for its dramatic mountain scenery, rich flora and fauna, and outdoor recreation opportunities.
  • E. Cape Flats
    The Cape Flats is a low-lying, sandy plain on the outskirts of Cape Town, South Africa, known for its dense townships, socio-economic challenges, and cultural diversity.
  • 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_69a493f1ddf48190a99d54b00e99f8ce completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b943b41481909b24050ca7e78971 completed March 1, 2026, 10:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac42addb188190a26dd3071abf64d6 completed March 7, 2026, 3:22 p.m.
Created at: March 1, 2026, 7:42 p.m.