Triple

T21630207
Position Surface form Disambiguated ID Type / Status
Subject South African Broadcasting Corporation E533809 entity
Predicate languageOfBroadcast P3314 FINISHED
Object Venda 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: Venda | Statement: [South African Broadcasting Corporation, languageOfBroadcast, Venda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Venda
Context triple: [South African Broadcasting Corporation, languageOfBroadcast, Venda]
  • A. Venda chosen
    Venda is a Bantu language of the Venda people of South Africa and Zimbabwe, recognized as one of South Africa’s official languages.
  • B. Loja
    Loja is a city in southern Ecuador known as a cultural and musical center nestled in the Andean highlands.
  • C. Loja
    Loja is a historic town in the province of Granada, Spain, known for its strategic location between Granada and the coast and its role in the final stages of the Reconquista.
  • D. Venda Nova
    Venda Nova is a populous district in the northern part of Belo Horizonte, Brazil, known as a residential and commercial area served by the city's metro system.
  • E. Sellin Ost
    Sellin Ost is a railway station in the Baltic Sea resort town of Sellin on Germany’s island of Rügen, serving the historic narrow-gauge steam railway Rasender Roland.
  • 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_69e0c464fba881908d0ff2ac80511ce1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef521679fc81909c94d42439fda4ba completed April 27, 2026, 12:09 p.m.
Created at: April 16, 2026, 6:34 p.m.