Triple
T1411195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soweto |
E31807
|
entity |
| Predicate | hasNeighbourhood |
P4813
|
FINISHED |
| Object |
Dube
Dube is a residential neighborhood in Soweto, South Africa, known for its historical significance in the anti-apartheid struggle.
|
E163637
|
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: Dube | Statement: [Soweto, hasNeighbourhood, Dube]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dube Context triple: [Soweto, hasNeighbourhood, Dube]
-
A.
Maphelane
Maphelane is a coastal nature reserve in South Africa known for its high vegetated dunes, rich birdlife, and diverse estuarine and marine habitats within the iSimangaliso Wetland Park.
-
B.
Tshiphani
Tshiphani is a regional dialect of the Tshivenda language spoken by Venda communities in parts of southern Africa.
-
C.
Madikizela
Madikizela is the maiden surname of South African anti-apartheid activist and politician Winnie Madikizela-Mandela.
-
D.
Bongi
Bongi is a neighborhood located in the city of Recife, in northeastern Brazil.
-
E.
Mandla
Mandla is a town and administrative district headquarters in the central Indian state of Madhya Pradesh, known for its proximity to the Narmada River and nearby wildlife and forested areas.
- 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: Dube Triple: [Soweto, hasNeighbourhood, Dube]
Generated description
Dube is a residential neighborhood in Soweto, South Africa, known for its historical significance in the anti-apartheid struggle.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dube Target entity description: Dube is a residential neighborhood in Soweto, South Africa, known for its historical significance in the anti-apartheid struggle.
-
A.
Maphelane
Maphelane is a coastal nature reserve in South Africa known for its high vegetated dunes, rich birdlife, and diverse estuarine and marine habitats within the iSimangaliso Wetland Park.
-
B.
Tshiphani
Tshiphani is a regional dialect of the Tshivenda language spoken by Venda communities in parts of southern Africa.
-
C.
Madikizela
Madikizela is the maiden surname of South African anti-apartheid activist and politician Winnie Madikizela-Mandela.
-
D.
Bongi
Bongi is a neighborhood located in the city of Recife, in northeastern Brazil.
-
E.
Mandla
Mandla is a town and administrative district headquarters in the central Indian state of Madhya Pradesh, known for its proximity to the Narmada River and nearby wildlife and forested areas.
- 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_69a49919a994819086528951bc224775 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c3e1da988190bc7c187e193539b6 |
completed | March 1, 2026, 10:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad015a52a88190933e7337067e5364 |
completed | March 8, 2026, 4:55 a.m. |
| NEDg | Description generation | batch_69ad01eb335c81908775e89b8a0348cc |
completed | March 8, 2026, 4:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad029584308190af10520e928f890b |
completed | March 8, 2026, 5:01 a.m. |
Created at: March 1, 2026, 7:59 p.m.