Triple

T22951307
Position Surface form Disambiguated ID Type / Status
Subject Yao language E570024 entity
Predicate neighboringLanguages P16383 FINISHED
Object Makhuwa 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: Makhuwa | Statement: [Yao language, neighboringLanguages, Makhuwa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Makhuwa
Context triple: [Yao language, neighboringLanguages, Makhuwa]
  • A. Makhuwa chosen
    Makhuwa is a major Bantu language spoken primarily in northern Mozambique by the Makhuwa people.
  • B. Bakwena
    The Bakwena are a major Tswana-speaking ethnic group of Southern Africa, historically known for their influential chieftaincies in present-day Botswana and South Africa.
  • C. Zithande
    Zithande is a popular song by South African singer and songwriter Nomvula.
  • D. Masandawana
    Masandawana is the popular nickname of South African football club Mamelodi Sundowns F.C., one of the country’s most successful and widely supported teams.
  • E. Makhado
    Makhado is a major town in South Africa’s Limpopo province, serving as an important commercial and administrative center in the Vhembe region.
  • 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_69e2459199d08190a8184ee2aa935842 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f181a285448190a718734fe933d51a completed April 29, 2026, 3:57 a.m.
Created at: April 17, 2026, 3:46 p.m.