Triple

T23004458
Position Surface form Disambiguated ID Type / Status
Subject Mokgibo E572722 entity
Predicate languageContext P36 FINISHED
Object Sepedi 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: Sepedi | Statement: [Mokgibo, languageContext, Sepedi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sepedi
Context triple: [Mokgibo, languageContext, Sepedi]
  • A. Tshivenda
    Tshivenda is a Bantu language spoken primarily by the Venda people in northern South Africa and neighboring regions.
  • B. Northern Sotho (Sepedi) chosen
    Northern Sotho (Sepedi) is a Bantu language of South Africa, recognized as one of the country’s official languages and widely spoken in the northern regions, especially in Limpopo and parts of Gauteng.
  • C. Sotho
    Sotho is a Bantu language of Southern Africa, primarily spoken in Lesotho and South Africa, where it serves as one of the country’s official languages.
  • D. Siswati
    Siswati is a Bantu language of the Nguni group spoken primarily in Eswatini and South Africa, where it holds official status.
  • E. Zulu
    Zulu is a Bantu language of the Nguni group spoken primarily in South Africa and widely influential in the country’s culture and other local languages.
  • 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_69e245b6a3ac81908087599eefe3e365 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183556cd08190b18780680bc4f23e completed April 29, 2026, 4:04 a.m.
Created at: April 17, 2026, 3:51 p.m.