Triple

T14082934
Position Surface form Disambiguated ID Type / Status
Subject Caprivi Strip E338911 entity
Predicate languageSpoken P151 FINISHED
Object Mbukushu
Mbukushu is a Bantu language spoken by the Mbukushu people primarily in northeastern Namibia and neighboring regions of Botswana and Angola.
 E1078473 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: Mbukushu | Statement: [Caprivi Strip, languageSpoken, Mbukushu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mbukushu
Context triple: [Caprivi Strip, languageSpoken, Mbukushu]
  • A. Mzuzu
    Mzuzu is a major city in northern Malawi known as an important commercial and administrative center for the region.
  • B. Mberengwa
    Mberengwa is a rural district and growth point in Zimbabwe known for its mining activities and location in the southern part of the Midlands Province.
  • C. Msikaba
    Msikaba is a coastal area in South Africa’s Eastern Cape known for its rugged shoreline, river gorge, and rich biodiversity near the Mkambati Nature Reserve.
  • D. Mvila
    Mvila is an administrative department in Cameroon's South Region, known for its local governance role and regional cultural diversity.
  • E. Mzembi
    Mzembi is the surname of Walter Mzembi, a Zimbabwean politician who served as Minister of Tourism and Hospitality Industry.
  • 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: Mbukushu
Triple: [Caprivi Strip, languageSpoken, Mbukushu]
Generated description
Mbukushu is a Bantu language spoken by the Mbukushu people primarily in northeastern Namibia and neighboring regions of Botswana and Angola.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mbukushu
Target entity description: Mbukushu is a Bantu language spoken by the Mbukushu people primarily in northeastern Namibia and neighboring regions of Botswana and Angola.
  • A. Mzuzu
    Mzuzu is a major city in northern Malawi known as an important commercial and administrative center for the region.
  • B. Mberengwa
    Mberengwa is a rural district and growth point in Zimbabwe known for its mining activities and location in the southern part of the Midlands Province.
  • C. Msikaba
    Msikaba is a coastal area in South Africa’s Eastern Cape known for its rugged shoreline, river gorge, and rich biodiversity near the Mkambati Nature Reserve.
  • D. Mvila
    Mvila is an administrative department in Cameroon's South Region, known for its local governance role and regional cultural diversity.
  • E. Mzembi
    Mzembi is the surname of Walter Mzembi, a Zimbabwean politician who served as Minister of Tourism and Hospitality Industry.
  • 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_69d81c687b0c819087fd9ed4198403f8 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5ede40048190b465e909565730c1 completed April 14, 2026, 3:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb6749c3c81909833a0b6ddcae3fb completed May 7, 2026, 3:57 p.m.
NEDg Description generation batch_69fcc44b8f3c8190a7dc5a98239be1a5 completed May 7, 2026, 4:56 p.m.
NED2 Entity disambiguation (via description) batch_69fcc4d99f608190a6dddfda19bf0685 completed May 7, 2026, 4:59 p.m.
Created at: April 9, 2026, 10:21 p.m.