Triple

T14151936
Position Surface form Disambiguated ID Type / Status
Subject Silozi E350703 entity
Predicate hasDialects P4251 FINISHED
Object Kwandi
Kwandi is a regional dialect of the Silozi language spoken by communities in parts of southern Africa.
E1084377 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: Kwandi | Statement: [Silozi, hasDialects, Kwandi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kwandi
Context triple: [Silozi, hasDialects, Kwandi]
  • A. Mafadi
    Mafadi is a prominent mountain peak on the border of South Africa and Lesotho, renowned as the highest point in South Africa and a popular destination for serious hikers and mountaineers.
  • B. Kwando
    Kwando is a river in southern Africa that flows through Angola, Namibia, and Botswana, forming part of the region’s complex wetland and river system.
  • C. Gundwane Ndiweni
    Gundwane Ndiweni was a prominent 19th-century Ndebele military and political leader associated with the royal House of Khumalo in what is now Zimbabwe.
  • D. Kwadi
    Kwadi is an extinct and poorly documented language of southwestern Angola, thought to be related to the Khoe languages within the proposed Khoe-Kwadi family.
  • E. Mokoena
    Mokoena is a common Southern African surname of Sotho-Tswana origin borne by various notable figures in politics, sports, and the arts.
  • 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: Kwandi
Triple: [Silozi, hasDialects, Kwandi]
Generated description
Kwandi is a regional dialect of the Silozi language spoken by communities in parts of southern Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kwandi
Target entity description: Kwandi is a regional dialect of the Silozi language spoken by communities in parts of southern Africa.
  • A. Mafadi
    Mafadi is a prominent mountain peak on the border of South Africa and Lesotho, renowned as the highest point in South Africa and a popular destination for serious hikers and mountaineers.
  • B. Kwando
    Kwando is a river in southern Africa that flows through Angola, Namibia, and Botswana, forming part of the region’s complex wetland and river system.
  • C. Gundwane Ndiweni
    Gundwane Ndiweni was a prominent 19th-century Ndebele military and political leader associated with the royal House of Khumalo in what is now Zimbabwe.
  • D. Kwadi
    Kwadi is an extinct and poorly documented language of southwestern Angola, thought to be related to the Khoe languages within the proposed Khoe-Kwadi family.
  • E. Mokoena
    Mokoena is a common Southern African surname of Sotho-Tswana origin borne by various notable figures in politics, sports, and the arts.
  • 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_69d8278775fc8190b0802d22ca2f495d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6124e23481909e5132a40a1d8624 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7ea34408190830263d7f5a88ce9 completed May 7, 2026, 8:36 p.m.
NEDg Description generation batch_69fd067e73708190adcb4e1c2fbf210d completed May 7, 2026, 9:39 p.m.
NED2 Entity disambiguation (via description) batch_69fd0c5161dc8190a923c5b00dc5b53a completed May 7, 2026, 10:04 p.m.
Created at: April 10, 2026, 12:57 a.m.