Triple
T9003828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Accessibility shortcuts (macOS) |
E215095
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | assistive technology interface |
C8684
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: assistive technology interface Context triple: [Accessibility shortcuts (macOS), instanceOf, assistive technology interface]
-
A.
library service for people with disabilities
A library service for people with disabilities provides accessible materials, adaptive technologies, and personalized support to ensure equitable access to information, resources, and programs.
-
B.
screen reader
chosen
A screen reader is assistive software that converts on-screen text and interface elements into synthesized speech or braille output, enabling blind or visually impaired users to access and interact with digital content.
-
C.
reading accessibility tool
A reading accessibility tool is a software application or feature that adapts text presentation and interaction (e.g., font, spacing, contrast, read-aloud, and navigation) to make written content easier to perceive, understand, and use for people with diverse reading needs and abilities.
-
D.
intelligent personal assistant
An intelligent personal assistant is a software agent that uses artificial intelligence to understand user requests, manage tasks, and provide personalized information or services through natural language interaction.
-
E.
human–computer interaction tool
A human–computer interaction tool is a software or hardware system designed to facilitate, enhance, or study the ways humans interact with computers through various input, output, and feedback mechanisms.
- F. None of above.
Provenance (1 batch)
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_69ca83a12d648190b1e4fe11e8a31890 |
completed | March 30, 2026, 2:07 p.m. |
Created at: March 30, 2026, 7:05 p.m.