Triple

T15876501
Position Surface form Disambiguated ID Type / Status
Subject Zaghawa people E384964 entity
Predicate region P40 FINISHED
Object Darfur E256794 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: Darfur | Statement: [Zaghawa people, region, Darfur]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Darfur
Context triple: [Zaghawa people, region, Darfur]
  • A. Darfur region chosen
    The Darfur region is a conflict-affected area in western Sudan known for its ethnic diversity, humanitarian crises, and international peacekeeping interventions.
  • B. Kordofan
    Kordofan is a historical and geographical region in central Sudan known for its semi-arid savannah, diverse ethnic groups, and role as a traditional trade and agricultural area.
  • C. North Darfur
    North Darfur is a conflict-affected state in western Sudan known for its arid landscape, scattered rural communities, and central role in the Darfur crisis.
  • D. West Darfur
    West Darfur is a conflict-affected state in western Sudan, forming the western part of the larger Darfur region and bordering Chad.
  • E. Central Darfur
    Central Darfur is a state in western Sudan, formed from the larger Darfur region and known for its ethnic diversity and history of conflict and humanitarian crises.
  • 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_69ffb043b6d48190bf9a36a3e00403c0 completed May 9, 2026, 10:08 p.m.
Created at: April 10, 2026, 4:51 a.m.