Triple

T3055445
Position Surface form Disambiguated ID Type / Status
Subject Dinka language E60468 entity
Predicate hasDialect P4251 FINISHED
Object Malual 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: Malual Dinka | Statement: [Dinka language, hasDialect, Malual Dinka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malual Dinka
Context triple: [Dinka language, hasDialect, Malual Dinka]
  • A. Dinka chosen
    Dinka is a Nilotic language spoken primarily by the Dinka people of South Sudan.
  • B. Kenuzi-Dongola
    Kenuzi-Dongola is a Nubian language of the Eastern Sudanic branch spoken primarily along the Nile in southern Egypt and northern Sudan.
  • C. Ovambo
    Ovambo is a Bantu language spoken primarily by the Ovambo people in northern Namibia and southern Angola.
  • D. Duwai
    Duwai is a West Chadic language spoken in parts of northern Nigeria.
  • E. Ouaddaï
    Ouaddaï is an eastern region of Chad known historically as the center of the former Wadai Sultanate and for its strategic location near the Sudanese border.
  • 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.