Triple

T5684050
Position Surface form Disambiguated ID Type / Status
Subject eThekwini Metropolitan Municipality E125267 entity
Predicate includesTown P847 FINISHED
Object Umlazi
Umlazi is a large township in the Durban area of South Africa, known as one of the country’s biggest urban settlements and a significant cultural and economic hub in KwaZulu-Natal.
E544792 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: Umlazi | Statement: [eThekwini Metropolitan Municipality, includesTown, Umlazi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Umlazi
Context triple: [eThekwini Metropolitan Municipality, includesTown, Umlazi]
  • A. Umtata
    Umtata is the former name of Mthatha, a town in South Africa’s Eastern Cape that serves as a regional economic and administrative center.
  • B. Mtiuleti
    Mtiuleti is a mountainous historical region in northeastern Georgia known for its rugged landscapes and traditional highland villages.
  • C. Mukuzani
    Mukuzani is a renowned Georgian red wine appellation known for producing dry, oak-aged wines from the Saperavi grape in the Kakheti region.
  • D. Makaziwe
    Makaziwe is a South African academic and businesswoman best known as the daughter of Nelson Mandela.
  • E. Mzuzu
    Mzuzu is a major city in northern Malawi known as an important commercial and administrative center for the region.
  • 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: Umlazi
Triple: [eThekwini Metropolitan Municipality, includesTown, Umlazi]
Generated description
Umlazi is a large township in the Durban area of South Africa, known as one of the country’s biggest urban settlements and a significant cultural and economic hub in KwaZulu-Natal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Umlazi
Target entity description: Umlazi is a large township in the Durban area of South Africa, known as one of the country’s biggest urban settlements and a significant cultural and economic hub in KwaZulu-Natal.
  • A. Umtata
    Umtata is the former name of Mthatha, a town in South Africa’s Eastern Cape that serves as a regional economic and administrative center.
  • B. Mtiuleti
    Mtiuleti is a mountainous historical region in northeastern Georgia known for its rugged landscapes and traditional highland villages.
  • C. Mukuzani
    Mukuzani is a renowned Georgian red wine appellation known for producing dry, oak-aged wines from the Saperavi grape in the Kakheti region.
  • D. Makaziwe
    Makaziwe is a South African academic and businesswoman best known as the daughter of Nelson Mandela.
  • E. Mzuzu
    Mzuzu is a major city in northern Malawi known as an important commercial and administrative center for the region.
  • 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_69c0082a884c8190a79001bae658941f completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c023b8efc4819085675d0d3dfb2a54 completed March 22, 2026, 5:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07dcb28888190affb0982060d5ea8 completed March 22, 2026, 11:39 p.m.
NEDg Description generation batch_69c08d7c1040819099f2f2fafdbc9627 completed March 23, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_69c08ddef5548190826d723551e99133 completed March 23, 2026, 12:48 a.m.
Created at: March 22, 2026, 3:44 p.m.