Triple
T20221249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple WWDC 2018 |
E495259
|
entity |
| Predicate | announced |
P429
|
FINISHED |
| Object | ARKit 2 |
—
|
NE NERFINISHED |
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: ARKit 2 | Statement: [Apple WWDC 2018, announced, ARKit 2]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ARKit 2 Context triple: [Apple WWDC 2018, announced, ARKit 2]
-
A.
ARKit framework
chosen
ARKit framework is Apple’s augmented reality development platform that enables iOS apps to blend virtual content with the real world using device cameras and motion sensors.
-
B.
RealityKit
RealityKit is Apple’s high-level 3D rendering and augmented reality framework used to build immersive spatial experiences on platforms like visionOS.
-
C.
SceneKit
SceneKit is a high-level 3D graphics framework from Apple used to build and render interactive 3D scenes and animations across its platforms.
-
D.
SpriteKit
SpriteKit is Apple’s 2D game development framework designed for building high-performance, animated games and interactive content across its platforms.
-
E.
Vision Pro
Vision Pro is Apple’s high-end mixed reality headset that blends augmented and virtual reality experiences using advanced displays, sensors, and custom Apple silicon.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da626cff80819097b530718a7c98b6 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66fd610f881908fdd22b1f8bd2efc |
completed | April 20, 2026, 6:26 p.m. |
Created at: April 11, 2026, 11:39 p.m.