Triple

T23043860
Position Surface form Disambiguated ID Type / Status
Subject Cinyanja E573818 entity
Predicate neighboringLanguage P16383 FINISHED
Object Tumbuka 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: Tumbuka | Statement: [Cinyanja, neighboringLanguage, Tumbuka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tumbuka
Context triple: [Cinyanja, neighboringLanguage, Tumbuka]
  • A. Tumbuka chosen
    Tumbuka is a Bantu language spoken primarily in northern Malawi and parts of Zambia and Tanzania.
  • B. Chichewa
    Chichewa is a major Bantu language spoken primarily in Malawi and neighboring countries, serving as a national and widely used lingua franca in the region.
  • C. Southern Tumbuka
    Southern Tumbuka is a regional variety of the Tumbuka language spoken primarily in the southern parts of the Tumbuka-speaking area of Malawi and neighboring regions.
  • D. Azande language
    Azande language is a Ubangian language spoken primarily by the Azande people across parts of South Sudan, the Central African Republic, and the Democratic Republic of the Congo.
  • E. Shona
    Shona is a major Bantu language of Zimbabwe, widely spoken by the Shona people and used in education, media, and government.
  • 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_69e245b9c11481909d06c872214d21af completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18517083c8190a0850da5440e0a73 completed April 29, 2026, 4:12 a.m.
Created at: April 17, 2026, 3:54 p.m.