Triple
T5922527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Web APIs |
E131730
|
entity |
| Predicate | example |
P1259
|
FINISHED |
| Object | Fullscreen API |
E48505
|
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: Fullscreen API | Statement: [Web APIs, example, Fullscreen API]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fullscreen API Context triple: [Web APIs, example, Fullscreen API]
-
A.
Fullscreen API Standard
chosen
The Fullscreen API Standard is a web specification that defines how websites can programmatically display elements in full-screen mode across browsers.
-
B.
CSS Fullscreen Module Level 1
CSS Fullscreen Module Level 1 is a W3C specification that defines how CSS should behave and be applied when elements are presented in fullscreen mode.
-
C.
ScreenX
ScreenX is a premium cinema technology that expands movie visuals onto the side walls of the theater to create an immersive, panoramic viewing experience.
-
D.
Screenslaver
Screenslaver is a mind-controlling supervillain who uses hypnotic screens to manipulate people in the animated film *Incredibles 2*.
-
E.
OpenDirect
OpenDirect is an industry standard protocol that enables automated, programmatic buying of guaranteed digital advertising inventory directly from publishers.
- 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_69c0085a1ed08190a7e9a8b6323fd680 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c03804d9808190829a418adb7864aa |
completed | March 22, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0c041d4f08190863141b037b1c05f |
completed | March 23, 2026, 4:23 a.m. |
Created at: March 22, 2026, 4 p.m.