Triple

T11608932
Position Surface form Disambiguated ID Type / Status
Subject Thembu E275332 entity
Predicate ethnonym P4709 FINISHED
Object abaThembu E275332 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: abaThembu | Statement: [Thembu, ethnonym, abaThembu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: abaThembu
Context triple: [Thembu, ethnonym, abaThembu]
  • A. Thembu chosen
    The Thembu are a Xhosa-speaking South African ethnic group historically known as one of the prominent chiefdoms in the Eastern Cape region.
  • B. AmaBhaca
    AmaBhaca are a Southern African ethnic group, primarily found in South Africa’s Eastern Cape, known for their distinct Nguni language and cultural traditions.
  • C. Nquthu
    Nquthu is a small town in KwaZulu-Natal, South Africa, known for its rural character and historical significance in the region.
  • D. Siyamthanda
    Siyamthanda is the full first name of Siya Kolisi, the renowned South African rugby union player and World Cup–winning Springboks captain.
  • E. Thokoza
    Thokoza is a township in the East Rand region of Gauteng, South Africa, historically known for its role in anti-apartheid struggles and community activism.
  • 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_69d6aaf84b548190ac072e4fb89ae18f completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a04231d08190b8a07cd977d11ffa completed April 10, 2026, 7:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69e8a82381708190aa0e674603d5778a completed April 22, 2026, 10:51 a.m.
Created at: April 8, 2026, 9:38 p.m.