Triple
T23474696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thaba Chweu Local Municipality |
E570226
|
entity |
| Predicate | seat |
P75
|
FINISHED |
| Object | Lydenburg |
—
|
NE NERFINISHED |
How this triple was built (2 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: Lydenburg | Statement: [Thaba Chweu Local Municipality, seat, Lydenburg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lydenburg Context triple: [Thaba Chweu Local Municipality, seat, Lydenburg]
-
A.
Lydenburg
chosen
Lydenburg is a historic town in South Africa known for its early gold-mining heritage and proximity to scenic routes and nature reserves in the Mpumalanga province.
-
B.
Lutzenberg
Lutzenberg is a small municipality in the canton of Appenzell Ausserrhoden in northeastern Switzerland.
-
C.
Johannisburg
Johannisburg is the former German name for the town of Pisz in northeastern Poland, historically part of East Prussia.
-
D.
Vryburg
Vryburg is a large agricultural and commercial town in South Africa’s North West Province, historically known as a key cattle-farming and transport hub.
-
E.
Siedenburg
Siedenburg is a small municipality in Lower Saxony, Germany, situated within the rural Diepholz district.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245af8a88819084f2704f6d265a92 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a704e2a48190acb55f77a2124412 |
completed | April 29, 2026, 6:36 a.m. |
Created at: April 17, 2026, 6 p.m.