Triple

T11582628
Position Surface form Disambiguated ID Type / Status
Subject Tumbuka E274665 entity
Predicate hasDialects P4251 FINISHED
Object Central Tumbuka
Central Tumbuka is the principal variety of the Tumbuka language, widely spoken in northern Malawi and used as a standard form in education and media.
 E935928 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: Central Tumbuka | Statement: [Tumbuka, hasDialects, Central Tumbuka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Central Tumbuka
Context triple: [Tumbuka, hasDialects, Central Tumbuka]
  • A. Mbunda
    Mbunda is a Bantu language spoken primarily in Angola and Zambia, known for its rich oral traditions and role in the cultural identity of the Mbunda people.
  • B. Busoga
    Busoga is a traditional kingdom and region in eastern Uganda, inhabited mainly by the Basoga people and situated across the Nile from Buganda.
  • C. Lunda
    Lunda is a Bantu language spoken primarily by the Lunda people in parts of Zambia, Angola, and the Democratic Republic of the Congo.
  • D. Luba
    Luba is a coastal town and important port on the southern part of Bioko Island in Equatorial Guinea.
  • E. Luba
    The Luba are a major Bantu-speaking ethnic group of Central Africa, historically known for the powerful Luba Kingdom centered in what is now the Democratic Republic of the Congo.
  • 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: Central Tumbuka
Triple: [Tumbuka, hasDialects, Central Tumbuka]
Generated description
Central Tumbuka is the principal variety of the Tumbuka language, widely spoken in northern Malawi and used as a standard form in education and media.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Central Tumbuka
Target entity description: Central Tumbuka is the principal variety of the Tumbuka language, widely spoken in northern Malawi and used as a standard form in education and media.
  • A. Mbunda
    Mbunda is a Bantu language spoken primarily in Angola and Zambia, known for its rich oral traditions and role in the cultural identity of the Mbunda people.
  • B. Busoga
    Busoga is a traditional kingdom and region in eastern Uganda, inhabited mainly by the Basoga people and situated across the Nile from Buganda.
  • C. Lunda
    Lunda is a Bantu language spoken primarily by the Lunda people in parts of Zambia, Angola, and the Democratic Republic of the Congo.
  • D. Luba
    The Luba are a major Bantu-speaking ethnic group of Central Africa, historically known for the powerful Luba Kingdom centered in what is now the Democratic Republic of the Congo.
  • E. Luba
    Luba is a coastal town and important port on the southern part of Bioko Island in Equatorial Guinea.
  • 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_69d6aae6b14c81908dc5a74bad7591f9 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8904db5748190ae5f10ae86ccdf46 completed April 10, 2026, 5:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69e8a78d80448190a93ca0ebfbd7e3a4 completed April 22, 2026, 10:48 a.m.
NEDg Description generation batch_69e8af93e07c8190aecb040cac6db146 completed April 22, 2026, 11:23 a.m.
NED2 Entity disambiguation (via description) batch_69ee5b254a2081909cba97a6ecb10601 completed April 26, 2026, 6:36 p.m.
Created at: April 8, 2026, 9:38 p.m.