Triple
T17234335
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chrome Web Platform features |
E418320
|
entity |
| Predicate | includesAPI |
P126488
|
FINISHED |
| Object | Media Capture and Streams API |
E860276
|
NE 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: Media Capture and Streams API | Statement: [Chrome Web Platform features, includesAPI, Media Capture and Streams API]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Media Capture and Streams API Context triple: [Chrome Web Platform features, includesAPI, Media Capture and Streams API]
-
A.
Media Capture and Streams specification
chosen
The Media Capture and Streams specification is a W3C standard that defines how web applications can access and control audio and video streams from devices like cameras and microphones, enabling features such as getUserMedia in browsers.
-
B.
WebRTC
WebRTC is an open web technology that enables real-time audio, video, and data communication directly between browsers and devices without requiring plugins.
-
C.
MediaStreamTrack
MediaStreamTrack is a WebRTC API interface representing a single media source stream, such as an audio or video track, that can be transmitted, processed, or combined in real-time communications.
-
D.
Picture-in-Picture API
The Picture-in-Picture API is a web standard that lets sites display videos in a floating, always-on-top window independent of the main browser tab.
-
E.
Object Capture API
Object Capture API is an Apple developer tool that converts photos of real-world objects into detailed 3D models for use in apps and AR experiences.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d886d8e96081909870bff6c3d0bf09 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42dfa0a408190880804d463305867 |
completed | April 19, 2026, 1:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01676382388190ab82bd10bd53f59e |
completed | May 11, 2026, 5:21 a.m. |
Created at: April 10, 2026, 5:39 a.m.