Triple
T22598614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wolfberg Arch |
E574751
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Clanwilliam |
—
|
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: Clanwilliam | Statement: [Wolfberg Arch, near, Clanwilliam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clanwilliam Context triple: [Wolfberg Arch, near, Clanwilliam]
-
A.
Clanwilliam
chosen
Clanwilliam is a historic town in South Africa’s Western Cape, known as a gateway to the Cederberg mountains and for its rooibos tea production.
-
B.
Swartland
Swartland is a wine-producing and agricultural region in South Africa’s Western Cape, known for its dry-farmed vineyards and distinctive Rhône-style and old-vine wines.
-
C.
Stormberg
Stormberg is a mountainous region in South Africa known for its high plateaus, rugged terrain, and significant geological and historical features.
-
D.
Colesberg
Colesberg is a small historic town in South Africa’s Northern Cape, known as a key stopover on the N1 highway and a gateway to the semi-arid Karoo region.
-
E.
Colenso
Colenso is a small town in South Africa’s KwaZulu-Natal province, historically known for its role in the Anglo-Zulu and Anglo-Boer wars.
- 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_69e245bc11308190b69d794d5d1e0bb6 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1626aa0808190a43e65f6aaabfeb4 |
completed | April 29, 2026, 1:44 a.m. |
Created at: April 17, 2026, 2:50 p.m.