Triple
T20989748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KwaDukuza–Durban corridor |
E516988
|
entity |
| Predicate | followsTransportRoute |
P125947
|
FINISHED |
| Object | N2 highway |
—
|
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: N2 highway | Statement: [KwaDukuza–Durban corridor, followsTransportRoute, N2 highway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsTransportRoute Context triple: [KwaDukuza–Durban corridor, followsTransportRoute, N2 highway]
-
A.
followsRouteOf
Indicates that one entity travels along the same path or route that another entity takes or has taken.
-
B.
hasTransportRoute
Indicates that there exists a designated transportation connection or route linking one entity to another.
-
C.
followsTransportCorridorAcross
chosen
Indicates that one entity’s path or alignment runs along and crosses a defined transport corridor (such as a road, railway, or canal) over some distance.
-
D.
routeNumberFollowedBy
Indicates that one route number directly succeeds another in a defined ordering or sequence.
-
E.
followsVehicle
Indicates that one vehicle is moving behind and in the same direction as another vehicle, maintaining a following position.
- 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_69e0b4ffac148190bbade9f0eceb660b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fbe5f49c8190a5c031eceba9ebf7 |
completed | April 21, 2026, 4:24 a.m. |
| PD | Predicate disambiguation | batch_69e5dbec80708190a49bccab7ff97e7b |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:49 p.m.