Triple

T1226281
Position Surface form Disambiguated ID Type / Status
Subject Winnie Mandela E26333 entity
Predicate ethnicGroup P194 FINISHED
Object Xhosa E11008 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: Xhosa | Statement: [Winnie Mandela, ethnicGroup, Xhosa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Xhosa
Context triple: [Winnie Mandela, ethnicGroup, Xhosa]
  • A. Xhosa chosen
    Xhosa is a Bantu language of South Africa, known for its distinctive click consonants and as one of the country’s major official languages.
  • B. Xitsonga
    Xitsonga is a Bantu language spoken primarily by the Tsonga people in southern Africa, notably in South Africa, Mozambique, and Zimbabwe.
  • C. Tshivenda
    Tshivenda is a Bantu language spoken primarily by the Venda people in northern South Africa and neighboring regions.
  • D. 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.
  • E. Sesotho
    Sesotho is a Southern Bantu language spoken primarily in Lesotho and South Africa, where it holds official status and serves as a major medium of communication and cultural identity.
  • 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_69a49484688c8190a1bf285eb396a8b6 completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be39908481908cca21aaf0828415 completed March 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69adbf379d048190924ad8dfa9ac5e7a completed March 8, 2026, 6:25 p.m.
Created at: March 1, 2026, 7:47 p.m.