Triple

T3055449
Position Surface form Disambiguated ID Type / Status
Subject Dinka language E60468 entity
Predicate hasDialect P4251 FINISHED
Object Southwestern Dinka E175971 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: Southwestern Dinka | Statement: [Dinka language, hasDialect, Southwestern Dinka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Southwestern Dinka
Context triple: [Dinka language, hasDialect, Southwestern Dinka]
  • A. Dinka people
    The Dinka people are a Nilotic ethnic group native to South Sudan, known for their pastoralist traditions, cattle culture, and significant role in the country’s history and society.
  • B. Shilluk
    The Shilluk are a Nilotic ethnic group of South Sudan known for their historical kingdom along the White Nile and rich oral traditions.
  • C. Nyuong Nuer
    Nyuong Nuer is a regional dialect of the Nuer language spoken by the Nyuong subgroup of the Nuer people in South Sudan and neighboring areas.
  • D. Ennedi
    Ennedi is a remote region in northeastern Chad renowned for its dramatic sandstone massifs, rock arches, and prehistoric rock art.
  • E. Dinka chosen
    Dinka is a Nilotic language spoken primarily by the Dinka people of South 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_69b2034c337481909c1b1ae304b89c24 completed March 12, 2026, 12:05 a.m.
Created at: March 8, 2026, 3:02 p.m.