Triple
T23221365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Withdean Stadium |
E580901
|
entity |
| Predicate | parkingRestrictions |
P3380
|
FINISHED |
| Object | limited on-site parking |
—
|
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: limited on-site parking | Statement: [Withdean Stadium, parkingRestrictions, limited on-site parking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parkingRestrictions Context triple: [Withdean Stadium, parkingRestrictions, limited on-site parking]
-
A.
parkingRequirement
Indicates the specified conditions or obligations related to providing or using parking associated with an entity or activity.
-
B.
pedestrianRestrictions
Indicates that there are specific rules or limitations governing where or how pedestrians may travel or access an area.
-
C.
parkingOften
Indicates that an entity frequently engages in the action of parking, or that parking occurs often in relation to that entity.
-
D.
trafficRestriction
Indicates a limitation or prohibition on the movement or flow of traffic between entities, such as vehicles, routes, or areas.
-
E.
parkingType
chosen
Indicates the specific kind or category of parking arrangement associated with an entity (e.g., street, garage, lot, reserved).
- 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1922924308190a26b00e09ce60ecd |
completed | April 29, 2026, 5:07 a.m. |
| PD | Predicate disambiguation | batch_69effcccee508190a7ae311fdd319806 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:08 p.m.