Triple

T2435563
Position Surface form Disambiguated ID Type / Status
Subject Venda E52951 entity
Predicate hasDialects P4251 FINISHED
Object Tshimanda E128482 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: Tshimanda | Statement: [Venda, hasDialects, Tshimanda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tshimanda
Context triple: [Venda, hasDialects, Tshimanda]
  • A. Tshimanda chosen
    Tshimanda is a regional dialect of the Tshivenda language spoken by a specific community of Venda people in South Africa.
  • B. Tshiluba
    Tshiluba is a Bantu language widely spoken in south-central Democratic Republic of the Congo, particularly in the Kasai region.
  • C. Chitambo
    Chitambo is a historical locality in present-day Zambia best known as the place where Scottish explorer David Livingstone died in 1873.
  • D. Ndesandjo
    Ndesandjo is the surname of Mark Obama Ndesandjo, an American businessman, musician, and author who is the half-brother of former U.S. President Barack Obama.
  • E. Inshuti Mu Buzima
    Inshuti Mu Buzima is the Rwandan branch of Partners In Health, working with the government to strengthen the health system and deliver high-quality care in rural communities.
  • 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_69ab4959bcc0819083246f9fb10439e3 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abc9cd49b48190bff10a5ab7cef483 completed March 7, 2026, 6:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69aebf6e23088190b0ce2feaa3eddda4 completed March 9, 2026, 12:39 p.m.
Created at: March 6, 2026, 9:43 p.m.