Triple

T6237165
Position Surface form Disambiguated ID Type / Status
Subject N2 national road E139504 entity
Predicate connectsTo P845 FINISHED
Object Empangeni
Empangeni is a town in KwaZulu-Natal, South Africa, situated near Richards Bay and known as a regional commercial and service center.
 E579267 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: Empangeni | Statement: [N2 national road, connectsTo, Empangeni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Empangeni
Context triple: [N2 national road, connectsTo, Empangeni]
  • A. Lilangeni
    The lilangeni is the official monetary unit of Eswatini, subdivided into 100 cents and commonly used alongside the South African rand.
  • B. Nomvula
    "Nomvula" is a popular album and title track by South African Afro-fusion band Freshlyground that helped bring them widespread recognition.
  • C. Hlengwe
    Hlengwe is a regional dialect of the Tsonga language spoken by Tsonga communities in parts of southern Africa.
  • D. Lomwe
    Lomwe is a Bantu language spoken primarily in Mozambique and Malawi by the Lomwe people.
  • E. Mpondo
    The Mpondo are a Southern African ethnic group closely related to the Xhosa, known for their distinct language variety, cultural traditions, and historical kingdom in what is now South Africa’s Eastern Cape.
  • 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: Empangeni
Triple: [N2 national road, connectsTo, Empangeni]
Generated description
Empangeni is a town in KwaZulu-Natal, South Africa, situated near Richards Bay and known as a regional commercial and service center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Empangeni
Target entity description: Empangeni is a town in KwaZulu-Natal, South Africa, situated near Richards Bay and known as a regional commercial and service center.
  • A. Lilangeni
    The lilangeni is the official monetary unit of Eswatini, subdivided into 100 cents and commonly used alongside the South African rand.
  • B. Nomvula
    "Nomvula" is a popular album and title track by South African Afro-fusion band Freshlyground that helped bring them widespread recognition.
  • C. Hlengwe
    Hlengwe is a regional dialect of the Tsonga language spoken by Tsonga communities in parts of southern Africa.
  • D. Lomwe
    Lomwe is a Bantu language spoken primarily in Mozambique and Malawi by the Lomwe people.
  • E. Mpondo
    The Mpondo are a Southern African ethnic group closely related to the Xhosa, known for their distinct language variety, cultural traditions, and historical kingdom in what is now South Africa’s Eastern Cape.
  • 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_69c008b0e7ac8190808a59573ee646f3 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c063021258819093a9237041816638 completed March 22, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69c243ff29248190abbb748601039f60 completed March 24, 2026, 7:57 a.m.
NEDg Description generation batch_69c2461400288190ba131686752b2ab7 completed March 24, 2026, 8:06 a.m.
NED2 Entity disambiguation (via description) batch_69c2467575848190abf321404a8df3c4 completed March 24, 2026, 8:08 a.m.
Created at: March 22, 2026, 4:23 p.m.