Triple
T21482821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | R534 road |
E530037
|
entity |
| Predicate | hasProvinceRoadSystem |
P74765
|
FINISHED |
| Object | South African regional route network |
—
|
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: South African regional route network | Statement: [R534 road, hasProvinceRoadSystem, South African regional route network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProvinceRoadSystem Context triple: [R534 road, hasProvinceRoadSystem, South African regional route network]
-
A.
hasRoadNumberSystem
Indicates that a place or region uses a specific system for assigning numbers to its roads or highways.
-
B.
hasRoads
Indicates that there exist constructed road connections linking the related entities.
-
C.
hasRoadNetworkType
chosen
Indicates the type or classification of road network associated with or present in an entity.
-
D.
roadSystem
Indicates a relationship where multiple roads are organized and connected as part of a larger, integrated transportation network or infrastructure.
-
E.
hasVoivodeshipRoad
Indicates that an entity is connected to or served by a specific voivodeship (regional) road.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea34c4388190adc78d209d2aafb8 |
completed | April 23, 2026, 9:45 a.m. |
| PD | Predicate disambiguation | batch_69e631ec1d048190b6da97da8222e413 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:21 p.m.