Triple
T34201593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johannesburg metropolitan road network |
E877399
|
entity |
| Predicate | containsRoadClass |
P74765
|
FINISHED |
| Object | metropolitan route (M roads) |
—
|
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: metropolitan route (M roads) | Statement: [Johannesburg metropolitan road network, containsRoadClass, metropolitan route (M roads)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsRoadClass Context triple: [Johannesburg metropolitan road network, containsRoadClass, metropolitan route (M roads)]
-
A.
hasRoadClass
Indicates that a road segment is assigned to a particular classification or category based on its type or functional importance.
-
B.
hasRoadNetworkType
chosen
Indicates the type or classification of road network associated with or present in an entity.
-
C.
appliesToRoadType
Indicates that a rule, condition, or attribute is specifically relevant or valid for a particular type or category of road.
-
D.
hasRoadComponent
Indicates that something includes, contains, or is composed of a specific road-related part or element.
-
E.
hasAccessRoadType
Indicates that an entity is connected to or served by a road of a specified access type (e.g., public, private, restricted).
- 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_69f349aff5f0819096275315abea5344 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a0061454944819088a0babfe60f69fc |
completed | May 10, 2026, 10:43 a.m. |
| PD | Predicate disambiguation | batch_6a0060b9ee108190b91e8d99a16f2b30 |
completed | May 10, 2026, 10:40 a.m. |
Created at: May 1, 2026, 1:55 a.m.