Triple
T14099085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hottentots Holland Mountains |
E339331
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Grabouw |
E536081
|
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: Grabouw | Statement: [Hottentots Holland Mountains, near, Grabouw]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grabouw Context triple: [Hottentots Holland Mountains, near, Grabouw]
-
A.
Grabouw
chosen
Grabouw is a town in South Africa’s Western Cape, known for its apple and pear orchards and scenic setting in the Elgin Valley near the Kogelberg mountains.
-
B.
Ozinga
Ozinga is a Dutch surname most notably associated with individuals such as Sjoukje Ozinga.
-
C.
Castrisch
Castrisch is a village and former municipality in the canton of Graubünden in eastern Switzerland, known for its location in the Surselva region.
-
D.
Greeff
Greeff is a surname of likely Afrikaans or Dutch origin borne by individuals such as Jacoba Elizabeth Greeff.
-
E.
Andries
Andries is a Dutch given name traditionally used for men, equivalent to Andrew in English.
- 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_69d81c69b5c8819094aa1abf18302908 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5fba7c10819095b1299b7b4f0310 |
completed | April 14, 2026, 3:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd0adfc28819097a1bfd56739c286 |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:22 p.m.