Triple
T17631124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | speed skating at the 2022 Winter Paralympics |
E429976
|
entity |
| Predicate | typeOfImpairment |
P122860
|
FINISHED |
| Object | physical impairment |
—
|
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: physical impairment | Statement: [speed skating at the 2022 Winter Paralympics, typeOfImpairment, physical impairment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfImpairment Context triple: [speed skating at the 2022 Winter Paralympics, typeOfImpairment, physical impairment]
-
A.
hasImpairmentStatus
chosen
Indicates that an entity possesses a particular condition of functional limitation, disability, or impairment status.
-
B.
hasSenseImpairment
Indicates that an entity experiences a reduction or loss in one or more sensory abilities (such as sight, hearing, or touch).
-
C.
canImpair
Indicates that one entity has the potential or ability to weaken, damage, or reduce the normal function, quality, or effectiveness of another entity.
-
D.
causeOfDisability
Indicates that one entity is the reason or source that brings about another entity’s disability.
-
E.
hasImpairmentListing
Indicates that an entity is associated with a specific recognized category or listing of impairments.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46dc192dc8190854f1fe5d5ed696a |
completed | April 19, 2026, 5:53 a.m. |
| PD | Predicate disambiguation | batch_69e3cddc87188190ac2f049b86038676 |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 5:52 a.m.