Triple
T11687105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saldanha Bay Local Municipality |
E277771
|
entity |
| Predicate | seat |
P75
|
FINISHED |
| Object | Vredenburg |
E274667
|
NE FINISHED |
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: Vredenburg | Statement: [Saldanha Bay Local Municipality, seat, Vredenburg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vredenburg Context triple: [Saldanha Bay Local Municipality, seat, Vredenburg]
-
A.
Vredenburg
chosen
Vredenburg is a town on South Africa’s West Coast that serves as a regional commercial and service hub near Saldanha Bay.
-
B.
Valkenburg
Valkenburg is a village in the Dutch province of South Holland, known for its historic charm and proximity to the North Sea coast.
-
C.
Zurenborg
Zurenborg is a historic and architecturally distinctive district in Antwerp, Belgium, renowned for its eclectic and Art Nouveau townhouses.
-
D.
Woudenberg
Woudenberg is a small Dutch municipality and town located in the central Netherlands.
-
E.
Doesburg
Doesburg is a historic city in the Dutch province of Gelderland, known for its well-preserved medieval center and location at the confluence of the IJssel and Oude IJssel rivers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6aafe02d881909900d54ad7d4af84 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4654be881909bd0256cf18e25de |
completed | April 10, 2026, 7:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef831d27248190894ffdb12c1ddd4d |
completed | April 27, 2026, 3:39 p.m. |
Created at: April 8, 2026, 9:40 p.m.