Triple
T12883556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Finkelstein |
E308163
|
entity |
| Predicate | mobilityAid |
P60789
|
FINISHED |
| Object | wheelchair |
—
|
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 | Statement: [Dr. Finkelstein, mobilityAid, wheelchair]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mobilityAid Context triple: [Dr. Finkelstein, mobilityAid, wheelchair]
-
A.
wheelchairAccessibility
Indicates whether a place, service, or route is accessible and usable by people who use wheelchairs.
-
B.
usesWheelchair
chosen
Indicates that an entity relies on or operates a wheelchair for mobility or transportation.
-
C.
supportsMobilityType
Indicates that one entity provides compatibility with, or can function using, a specified type of mobility or movement mode.
-
D.
mobilityComponent
Indicates that one entity functions as a mobility-related component or module that enables or affects the movement capabilities of another entity.
-
E.
mobilityCharacteristic
Indicates a relationship where an entity is described or classified in terms of its movement or transportation-related properties, such as how, how well, or under what conditions it can move or be moved.
- 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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97c7f91d08190aac2f6419d3ba992 |
completed | April 10, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69d96fa55b888190ab1612e93c41aec4 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:39 p.m.