Triple

T22253509
Position Surface form Disambiguated ID Type / Status
Subject Kingwana dialect E550038 entity
Predicate closelyRelatedTo P37 FINISHED
Object Standard Swahili 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: Standard Swahili | Statement: [Kingwana dialect, closelyRelatedTo, Standard Swahili]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Standard Swahili
Context triple: [Kingwana dialect, closelyRelatedTo, Standard Swahili]
  • A. Swahili language chosen
    Swahili is a major Bantu language widely spoken in East and Central Africa, serving as a regional lingua franca and an official language in several countries including Tanzania and Kenya.
  • B. Mwimbi dialect
    The Mwimbi dialect is a regional variety of the Bantu Meru language spoken by the Mwimbi people in eastern Kenya.
  • C. Swahili Wiktionary
    Swahili Wiktionary is the Swahili-language edition of Wiktionary, a collaborative online dictionary and lexical resource for Swahili words and terms.
  • D. Swahili Wikiquote
    Swahili Wikiquote is the Swahili-language edition of Wikiquote, a free online collection of sourced quotations from notable people, books, films, and other creative works.
  • E. Swahili Wikipedia
    Swahili Wikipedia is the Swahili-language edition of the free, collaboratively edited online encyclopedia Wikipedia.
  • 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_69e11e42adb8819087714772ea606709 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f138c0c4f48190a75473a7835014f1 completed April 28, 2026, 10:46 p.m.
Created at: April 16, 2026, 8:39 p.m.