Triple

T8112832
Position Surface form Disambiguated ID Type / Status
Subject Rukwa Region E189396 entity
Predicate hasSettlement P1068 FINISHED
Object Nkasi
Nkasi is a district and town located in Tanzania's western Rukwa Region, near the shores of Lake Tanganyika.
 E712872 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: Nkasi | Statement: [Rukwa Region, hasSettlement, Nkasi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Nkasi
Context triple: [Rukwa Region, hasSettlement, Nkasi]
  • A. Nkambe
    Nkambe is a town and administrative center in northwestern Cameroon known for its role as the capital of Donga-Mantung Division.
  • B. Mukuzani
    Mukuzani is a renowned Georgian red wine appellation known for producing dry, oak-aged wines from the Saperavi grape in the Kakheti region.
  • C. Ngwenyama
    Ngwenyama is the traditional Swazi royal title meaning "lion," used for the reigning king of Eswatini.
  • D. Bongwe
    Bongwe is a dialect of the Duala language spoken by the Duala people of Cameroon.
  • E. Kazungula
    Kazungula is a border town in southern Africa, strategically located near the Zambezi River where Botswana, Zambia, Zimbabwe, and Namibia meet, and known for its important regional transport links.
  • 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: Nkasi
Triple: [Rukwa Region, hasSettlement, Nkasi]
Generated description
Nkasi is a district and town located in Tanzania's western Rukwa Region, near the shores of Lake Tanganyika.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Nkasi
Target entity description: Nkasi is a district and town located in Tanzania's western Rukwa Region, near the shores of Lake Tanganyika.
  • A. Nkambe
    Nkambe is a town and administrative center in northwestern Cameroon known for its role as the capital of Donga-Mantung Division.
  • B. Mukuzani
    Mukuzani is a renowned Georgian red wine appellation known for producing dry, oak-aged wines from the Saperavi grape in the Kakheti region.
  • C. Ngwenyama
    Ngwenyama is the traditional Swazi royal title meaning "lion," used for the reigning king of Eswatini.
  • D. Bongwe
    Bongwe is a dialect of the Duala language spoken by the Duala people of Cameroon.
  • E. Kazungula
    Kazungula is a border town in southern Africa, strategically located near the Zambezi River where Botswana, Zambia, Zimbabwe, and Namibia meet, and known for its important regional transport links.
  • 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_69ca82baad008190ab2859712b9b1607 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb432d7dfc8190b9c980f32c7b4623 completed March 31, 2026, 3:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc9433a5848190aac09a2589061b53 completed April 1, 2026, 3:42 a.m.
NEDg Description generation batch_69cc963fe2f8819098ad6a726e226189 completed April 1, 2026, 3:51 a.m.
NED2 Entity disambiguation (via description) batch_69cc97781c0481909d21293633d111be completed April 1, 2026, 3:56 a.m.
Created at: March 30, 2026, 5:32 p.m.