Triple
T30057542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NORTA |
E763772
|
entity |
| Predicate | providesAccessibilityFeature |
P80912
|
FINISHED |
| Object | wheelchair-accessible buses |
—
|
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: wheelchair-accessible buses | Statement: [NORTA, providesAccessibilityFeature, wheelchair-accessible buses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providesAccessibilityFeature Context triple: [NORTA, providesAccessibilityFeature, wheelchair-accessible buses]
-
A.
providesAccessibility
Indicates that one entity enables or improves access to another entity, resource, or service, removing or reducing barriers to its use.
-
B.
accessibilityFeatures
chosen
Indicates the specific tools, settings, or design elements provided to make something usable or understandable for people with disabilities or diverse access needs.
-
C.
hasAccessibilityVariation
Indicates that one entity differs from another in terms of accessibility features, conditions, or support.
-
D.
offersAccessibilityService
Indicates that an entity provides services or features designed to improve accessibility for people with disabilities or specific access needs.
-
E.
valueAccessibility
Indicates how easily or readily a value can be obtained, used, or understood by relevant parties.
- 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_69f224716378819087a722e487832b70 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd4129a8848190a5002150278ac689 |
completed | May 8, 2026, 1:49 a.m. |
| PD | Predicate disambiguation | batch_69fd3e0515ec8190937c7af71ebc3875 |
completed | May 8, 2026, 1:36 a.m. |
Created at: April 29, 2026, 6:56 p.m.