Triple

T19104016
Position Surface form Disambiguated ID Type / Status
Subject Greater Durban area E467605 entity
Predicate includesArea P1393 FINISHED
Object Isipingo
Isipingo is a coastal town in KwaZulu-Natal, South Africa, situated just south of Durban and known for its industrial zones and residential suburbs.
 E1358388 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: Isipingo | Statement: [Greater Durban area, includesArea, Isipingo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Isipingo
Context triple: [Greater Durban area, includesArea, Isipingo]
  • A. Ngumbi
    Ngumbi is a Bantu language spoken along the central coast of Cameroon, closely related to and sometimes considered a variety of Kombe.
  • B. Bolongongo
    Bolongongo is a town and municipality located in Angola’s Cuanza Norte Province.
  • C. Empangeni
    Empangeni is a town in KwaZulu-Natal, South Africa, situated near Richards Bay and known as a regional commercial and service center.
  • D. Chipinga
    Chipinga is the former name of Chipinge, a town in southeastern Zimbabwe known for its agriculture and proximity to the Mozambique border.
  • E. Bulange
    Bulange is the historic administrative building of the Buganda Kingdom in Kampala, Uganda, serving as the seat of the Lukiiko (parliament) and the Kabaka’s offices.
  • 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: Isipingo
Triple: [Greater Durban area, includesArea, Isipingo]
Generated description
Isipingo is a coastal town in KwaZulu-Natal, South Africa, situated just south of Durban and known for its industrial zones and residential suburbs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Isipingo
Target entity description: Isipingo is a coastal town in KwaZulu-Natal, South Africa, situated just south of Durban and known for its industrial zones and residential suburbs.
  • A. Ngumbi
    Ngumbi is a Bantu language spoken along the central coast of Cameroon, closely related to and sometimes considered a variety of Kombe.
  • B. Bolongongo
    Bolongongo is a town and municipality located in Angola’s Cuanza Norte Province.
  • C. Empangeni
    Empangeni is a town in KwaZulu-Natal, South Africa, situated near Richards Bay and known as a regional commercial and service center.
  • D. Chipinga
    Chipinga is the former name of Chipinge, a town in southeastern Zimbabwe known for its agriculture and proximity to the Mozambique border.
  • E. Bulange
    Bulange is the historic administrative building of the Buganda Kingdom in Kampala, Uganda, serving as the seat of the Lukiiko (parliament) and the Kabaka’s offices.
  • 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_69d8dd05ac4c8190b1967d8f97f3fb2f completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e36f84048190a62c52411eb55411 completed April 20, 2026, 8:27 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05dda026d48190a4d35291d49f497e completed May 14, 2026, 2:35 p.m.
NEDg Description generation batch_6a05dfcf14788190a75298641ba20e0e completed May 14, 2026, 2:44 p.m.
NED2 Entity disambiguation (via description) batch_6a05e10ae8188190a9dce95fa838ff7f completed May 14, 2026, 2:49 p.m.
Created at: April 10, 2026, 12:04 p.m.