Triple

T18369754
Position Surface form Disambiguated ID Type / Status
Subject Benga people E446149 entity
Predicate language P15 FINISHED
Object Benga language 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: Benga language | Statement: [Benga people, language, Benga language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Benga language
Context triple: [Benga people, language, Benga language]
  • A. Benga language chosen
    The Benga language is a Bantu language of the Niger-Congo family traditionally spoken by the Benga people in coastal areas of Equatorial Guinea and nearby islands.
  • B. Tembe language
    The Tembe language is an indigenous Tupi-Guarani language spoken by the Tembé people of northern Brazil.
  • C. Nsenga language
    The Nsenga language is a Bantu language spoken primarily in Zambia and neighboring regions, closely related to other languages of the area such as Tumbuka and Chewa.
  • D. Bongo language
    The Bongo language is a Central Sudanic language spoken by the Bongo people of South Sudan.
  • E. Karanga language
    The Karanga language is a member of the Maban branch of the Nilo-Saharan language family, spoken by communities in the central African region.
  • 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_69d8b9f370b88190b1e5081c2c238e7f completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e51751e4288190873bcc4dc140ac16 completed April 19, 2026, 5:56 p.m.
Created at: April 10, 2026, 10:43 a.m.