Triple

T21588041
Position Surface form Disambiguated ID Type / Status
Subject Kisukuma language E532703 entity
Predicate hasAlternativeName P39 FINISHED
Object Sukuma 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: Sukuma | Statement: [Kisukuma language, hasAlternativeName, Sukuma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sukuma
Context triple: [Kisukuma language, hasAlternativeName, Sukuma]
  • A. Sukuma chosen
    Sukuma is a major Bantu language spoken primarily by the Sukuma people in northern Tanzania.
  • B. Usutu River
    The Usutu River is a major river in southern Africa that flows through South Africa, Eswatini, and Mozambique before emptying into the Indian Ocean.
  • C. Juma River
    The Juma River is a scenic river in northern China known for flowing through karst gorges and popular outdoor recreation areas near Beijing.
  • D. Mwenezi River
    The Mwenezi River is a significant river in southern Africa that flows through Zimbabwe and Mozambique, supporting local agriculture, wildlife, and communities along its course.
  • E. Unzha River
    The Unzha River is a significant waterway in central Russia that flows through Kostroma and neighboring regions before joining the Volga River.
  • 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_69e0c46251648190876f0427cf2d321b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeeb621ab88190a33a943424ffb306 completed April 27, 2026, 4:51 a.m.
Created at: April 16, 2026, 6:31 p.m.