Triple

T3055450
Position Surface form Disambiguated ID Type / Status
Subject Dinka language E60468 entity
Predicate region P40 FINISHED
Object Bahr el Ghazal E262129 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: Bahr el Ghazal | Statement: [Dinka language, region, Bahr el Ghazal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bahr el Ghazal
Context triple: [Dinka language, region, Bahr el Ghazal]
  • A. Bahr el Ghazal chosen
    Bahr el Ghazal is a major river and region in South Sudan that forms one of the principal western tributary systems of the White Nile.
  • B. Central Sudan
    Central Sudan is a historical region in north-central Africa encompassing parts of modern-day northern Nigeria and surrounding areas, known for its precolonial emirates and trans-Saharan trade networks.
  • C. Ennedi
    Ennedi is a remote region in northeastern Chad renowned for its dramatic sandstone massifs, rock arches, and prehistoric rock art.
  • D. Arabi Juba
    Arabi Juba is a colloquial Arabic-based creole widely spoken as a lingua franca in and around Juba, South Sudan.
  • E. Kenuzi-Dongola
    Kenuzi-Dongola is a Nubian language of the Eastern Sudanic branch spoken primarily along the Nile in southern Egypt and northern Sudan.
  • 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_69ad8578137c81908259dcb27c7d6d7c completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ad9bf6b9948190bc957bfd1579c471 completed March 8, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1ef03425c8190a44486ab563c210f completed March 11, 2026, 10:38 p.m.
Created at: March 8, 2026, 3:02 p.m.