Triple
T27836425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kinect sensor |
E703238
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | voice recognition device |
C5203
|
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: voice recognition device Context triple: [Kinect sensor, instanceOf, voice recognition device]
-
A.
speech recognition API
A speech recognition API is a software interface that converts spoken language into machine-readable text or commands, enabling applications to process and respond to voice input.
-
B.
voice-driven application
A voice-driven application is a software system that allows users to interact and perform tasks primarily through spoken commands and natural language input.
-
C.
voice recognition company
A voice recognition company develops and provides technologies that enable computers and devices to accurately interpret, process, and respond to human speech for applications such as virtual assistants, transcription, and voice-controlled interfaces.
-
D.
voice application platform feature
A voice application platform feature is a functional capability within a voice-enabled system that allows developers or users to create, manage, and enhance interactive voice experiences through tools like speech recognition, natural language understanding, and integration with external services.
-
E.
automatic speech recognition system
chosen
An automatic speech recognition system converts spoken language into written text by analyzing and interpreting audio signals using acoustic, linguistic, and statistical models.
- 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_69ef840b94b08190950a4f77296938b2 |
completed | April 27, 2026, 3:43 p.m. |
Created at: April 27, 2026, 5:59 p.m.