Triple
T24376236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Africa–Mozambique border |
E614481
|
entity |
| Predicate | majorRoadCrossing |
P33132
|
FINISHED |
| Object | N4 highway (South Africa) |
—
|
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: N4 highway (South Africa) | Statement: [South Africa–Mozambique border, majorRoadCrossing, N4 highway (South Africa)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorRoadCrossing Context triple: [South Africa–Mozambique border, majorRoadCrossing, N4 highway (South Africa)]
-
A.
mainRoadCrossingBetween
Indicates that a primary or main road intersects or passes between two specified locations or entities.
-
B.
crossedByHighway
chosen
Indicates that a highway passes across or through the extent of a given entity or area.
-
C.
crossesStreet
Indicates that an entity moves from one side of a street to the other, traversing the street’s width.
-
D.
isMajorRoadIn
Indicates that a road is classified as a major road within a specified geographic area or jurisdiction.
-
E.
hasMajorCrossing
Indicates that one entity has a significant or primary intersection or crossing with another entity.
- 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_69e2d7e1e010819098b95eb3f905943d |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f293d73c0c8190b80e257845a04c57 |
completed | April 29, 2026, 11:27 p.m. |
| PD | Predicate disambiguation | batch_69f287bb1b2c81909c2e7fcc392ad143 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:02 a.m.