Triple
T17981971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stanger, Natal, South Africa |
E449621
|
entity |
| Predicate | distanceToDurbanApproxKm |
P34438
|
FINISHED |
| Object | about 70 kilometres north of Durban |
—
|
LITERAL 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: about 70 kilometres north of Durban | Statement: [Stanger, Natal, South Africa, distanceToDurbanApproxKm, about 70 kilometres north of Durban]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceToDurbanApproxKm Context triple: [Stanger, Natal, South Africa, distanceToDurbanApproxKm, about 70 kilometres north of Durban]
-
A.
distanceToDurban_km
chosen
Indicates the physical distance, measured in kilometers, between a given location and the city of Durban.
-
B.
distanceToJohannesburg_km
Indicates the physical distance, measured in kilometers, between a given entity’s location and Johannesburg.
-
C.
distanceFromCapeTown
Indicates the measured distance between a given location and Cape Town.
-
D.
distanceToBloemfontein
Indicates the spatial distance between a given entity’s location and the city of Bloemfontein.
-
E.
approximateDistanceToJohannesburg
Indicates that one entity has an estimated or rough distance relationship to the location Johannesburg.
- F. None of above.
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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b297b7108190a676409b330ca23b |
completed | April 19, 2026, 10:46 a.m. |
| PD | Predicate disambiguation | batch_69e3f8fa62688190a5d5c361ab896256 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:22 a.m.