Triple

T9066738
Position Surface form Disambiguated ID Type / Status
Subject Old Nubian E217262 entity
Predicate hasDescendant P3654 FINISHED
Object Dongolawi E60598 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: Dongolawi | Statement: [Old Nubian, hasDescendant, Dongolawi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dongolawi
Context triple: [Old Nubian, hasDescendant, Dongolawi]
  • A. Dongolawi chosen
    Dongolawi is a Nubian language spoken primarily along the Nile in northern Sudan, known for its role in preserving the cultural and linguistic heritage of the Nubian people.
  • B. Anseba Region
    Anseba Region is an administrative region in Eritrea known for its diverse ethnic communities, including the Bilen people, and its mix of highland and lowland landscapes.
  • C. Nzara, Sudan
    Nzara, Sudan is a town in southwestern South Sudan notable as the site of the first recorded outbreak of Ebola virus disease in 1976.
  • D. Gash-Barka Region
    Gash-Barka Region is a largely rural administrative region in western Eritrea known for its agricultural importance and strategic location bordering Sudan and Ethiopia.
  • E. Takrur
    Takrur was an early West African kingdom located in the Senegal River valley, known for its role in trans-Saharan trade and its early adoption of Islam.
  • 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_69ca83d5a7f48190b16c1e59bd43ede0 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc94bde9c08190a4f568fbccc3c3e9 completed April 1, 2026, 3:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69d017a3926881909140f59c60ec3588 completed April 3, 2026, 7:40 p.m.
Created at: March 30, 2026, 7:11 p.m.