Triple

T10483303
Position Surface form Disambiguated ID Type / Status
Subject Sabaot E247225 entity
Predicate hasDialects P4251 FINISHED
Object Bongomek
Bongomek is a dialect of the Sabaot language spoken by a subgroup of the Sabaot people in East Africa.
 E865579 NE FINISHED

How this triple was built (4 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: Bongomek | Statement: [Sabaot, hasDialects, Bongomek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bongomek
Context triple: [Sabaot, hasDialects, Bongomek]
  • A. Kiyombe
    Kiyombe is a regional variety of the Kikongo language spoken by communities in parts of Central Africa.
  • B. Fomboni
    Fomboni is the largest town and administrative center of the island of Mohéli in the Comoros, known for its coastal setting and role as the island’s main port and commercial hub.
  • C. Ngoulemakong
    Ngoulemakong is a town located in the South Region of Cameroon.
  • D. Mohombi
    Mohombi is a Congolese-Swedish singer, songwriter, and dancer known for his international pop and dance hits blending African and European musical influences.
  • E. Lubemba
    Lubemba is the traditional kingdom and cultural heartland of the Bemba people in what is now northern Zambia.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Bongomek
Triple: [Sabaot, hasDialects, Bongomek]
Generated description
Bongomek is a dialect of the Sabaot language spoken by a subgroup of the Sabaot people in East Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bongomek
Target entity description: Bongomek is a dialect of the Sabaot language spoken by a subgroup of the Sabaot people in East Africa.
  • A. Kiyombe
    Kiyombe is a regional variety of the Kikongo language spoken by communities in parts of Central Africa.
  • B. Fomboni
    Fomboni is the largest town and administrative center of the island of Mohéli in the Comoros, known for its coastal setting and role as the island’s main port and commercial hub.
  • C. Ngoulemakong
    Ngoulemakong is a town located in the South Region of Cameroon.
  • D. Mohombi
    Mohombi is a Congolese-Swedish singer, songwriter, and dancer known for his international pop and dance hits blending African and European musical influences.
  • E. Lubemba
    Lubemba is the traditional kingdom and cultural heartland of the Bemba people in what is now northern Zambia.
  • F. None of above. chosen

Provenance (5 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_69d381c309b88190af78aa681cf6a4c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509678ac88190984f18a2162e2dcf completed April 7, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8a03c647c81909521fee4a66ec8ac completed April 10, 2026, 7:01 a.m.
NEDg Description generation batch_69d8a45e5a108190ba8e6ba4af858b19 completed April 10, 2026, 7:18 a.m.
NED2 Entity disambiguation (via description) batch_69d8a890c6b081908e57cc74f18d788b completed April 10, 2026, 7:36 a.m.
Created at: April 6, 2026, 12:22 p.m.