Triple

T21824888
Position Surface form Disambiguated ID Type / Status
Subject Taa E538823 entity
Predicate ethnicGroup P194 FINISHED
Object Taa-speaking San NE NERFINISHED

How this triple was built (3 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: Taa-speaking San | Statement: [Taa, ethnicGroup, Taa-speaking San]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taa-speaking San
Context triple: [Taa, ethnicGroup, Taa-speaking San]
  • A. Ngaro people
    The Ngaro people are an Aboriginal Australian group traditionally associated with the sea and island landscapes of the central Great Barrier Reef region in Queensland.
  • B. Haiǁom people
    The Haiǁom people are an indigenous Khoe-speaking community of southern Africa, traditionally associated with the Etosha region of Namibia and known for their hunter-gatherer heritage.
  • C. Luvale people
    The Luvale people are a Bantu-speaking ethnic group of northwestern Zambia and neighboring Angola, known for their rich oral traditions, initiation ceremonies, and distinctive artistic and musical heritage.
  • D. Munduruku people
    The Munduruku people are an Indigenous group of the Brazilian Amazon known for their rich cultural traditions, historical warrior reputation, and ongoing struggles to defend their territories and rivers from environmental threats.
  • E. Saluan people
    The Saluan people are an indigenous ethnic group of Central Sulawesi, Indonesia, known for their distinct Austronesian language and coastal-maritime cultural traditions.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Taa-speaking San
Target entity description: Taa-speaking San are an indigenous hunter-gatherer people of southern Africa who speak the Taa (ǃXóõ) language, noted for having one of the world’s most complex sound systems.
  • A. Ngaro people
    The Ngaro people are an Aboriginal Australian group traditionally associated with the sea and island landscapes of the central Great Barrier Reef region in Queensland.
  • B. Haiǁom people
    The Haiǁom people are an indigenous Khoe-speaking community of southern Africa, traditionally associated with the Etosha region of Namibia and known for their hunter-gatherer heritage.
  • C. Luvale people
    The Luvale people are a Bantu-speaking ethnic group of northwestern Zambia and neighboring Angola, known for their rich oral traditions, initiation ceremonies, and distinctive artistic and musical heritage.
  • D. Munduruku people
    The Munduruku people are an Indigenous group of the Brazilian Amazon known for their rich cultural traditions, historical warrior reputation, and ongoing struggles to defend their territories and rivers from environmental threats.
  • E. Saluan people
    The Saluan people are an indigenous ethnic group of Central Sulawesi, Indonesia, known for their distinct Austronesian language and coastal-maritime cultural traditions.
  • F. None of above. chosen

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_69e0c475038c8190abb9b1a20eb8ff50 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f091307d408190a92b65c3f39682a8 completed April 28, 2026, 10:51 a.m.
Created at: April 16, 2026, 6:54 p.m.