Triple

T15876494
Position Surface form Disambiguated ID Type / Status
Subject Zaghawa people E384964 entity
Predicate language P15 FINISHED
Object Zaghawa language E803591 NE FINISHED

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: Zaghawa language | Statement: [Zaghawa people, language, Zaghawa language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zaghawa language
Context triple: [Zaghawa people, language, Zaghawa language]
  • A. Zaghawa language chosen
    The Zaghawa language is an Eastern Saharan language spoken primarily by the Zaghawa people of Chad and western Sudan.
  • B. Manguissa language
    The Manguissa language is a Bantu language spoken by the Manguissa people of Cameroon, closely related to and geographically adjacent to Ewondo.
  • C. Effutu language
    Effutu language is a Niger-Congo language spoken primarily by the Effutu people in and around the coastal town of Winneba in Ghana.
  • D. Kadugli–Krongo languages
    Kadugli–Krongo languages are a small group of closely related, poorly documented languages spoken mainly in the Nuba Mountains of Sudan, often considered part of the Kadu language family.
  • E. Ngbandi language
    The Ngbandi language is a Central Sudanic language spoken primarily in the Central African Republic and the Democratic Republic of the Congo, known for being the linguistic source of the trade language Sango.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e155fdc1b881909d1c82c4c66a195a completed April 16, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa950a890819092bc1e8895034593 completed May 9, 2026, 9:38 p.m.
Created at: April 10, 2026, 4:51 a.m.