Triple
T34812458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyon–Grenoble axis |
E1003534
|
entity |
| Predicate | mainRoadInfrastructure |
P181507
|
FINISHED |
| Object | A43 motorway |
—
|
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: A43 motorway | Statement: [Lyon–Grenoble axis, mainRoadInfrastructure, A43 motorway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainRoadInfrastructure Context triple: [Lyon–Grenoble axis, mainRoadInfrastructure, A43 motorway]
-
A.
roadSystem
Indicates a relationship where multiple roads are organized and connected as part of a larger, integrated transportation network or infrastructure.
-
B.
roadSystemLevel
Indicates the classification or hierarchy level of a road within a broader transportation or road network system.
-
C.
majorTransportCorridor
Indicates that a route or pathway functions as a primary, high-capacity channel for transporting people or goods between significant locations.
-
D.
roadType
Indicates the classification or category of a road based on its functional or physical characteristics.
-
E.
arterialRoad
Indicates that a road functions as a primary high-capacity route that channels major traffic flows between different areas of a transport network.
- F. None of above. chosen
Provenance (4 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_69f76db600b88190989abdf08fce3b27 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f77ab6555c81909fcff2c0c8ef9793 |
completed | May 3, 2026, 4:41 p.m. |
| PD | Predicate disambiguation | batch_69f7795b1abc8190823664d1caa94649 |
completed | May 3, 2026, 4:35 p.m. |
| PDg | Predicate description generation | batch_69f77a39135081908ae22d2a23b44e74 |
completed | May 3, 2026, 4:39 p.m. |
Created at: May 3, 2026, 3:59 p.m.