Triple
T12164775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | iPhone 15 Pro |
E289801
|
entity |
| Predicate | supportsGamingFeature |
P203
|
FINISHED |
| Object | hardware-accelerated ray tracing |
—
|
LITERAL 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: hardware-accelerated ray tracing | Statement: [iPhone 15 Pro, supportsGamingFeature, hardware-accelerated ray tracing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsGamingFeature Context triple: [iPhone 15 Pro, supportsGamingFeature, hardware-accelerated ray tracing]
-
A.
supportsGameStreaming
Indicates that one entity provides the capability for another entity to stream and play games remotely in real time.
-
B.
supportsGameEngine
Indicates that one entity provides compatibility, functionality, or resources necessary for the operation or integration of a particular game engine.
-
C.
supports4KGaming
Indicates that the subject is capable of running or displaying games at 4K resolution.
-
D.
notableGameSupport
Indicates that an entity is recognized for providing significant support or contribution to a particular game.
-
E.
supportsFeature
chosen
Indicates that one entity provides, enables, or is compatible with a particular feature or capability of another.
- F. None of above.
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_69d6ab4d6c00819095a9a7c35de83cfb |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915d7109481908bf5fe512bba3c89 |
completed | April 10, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69d9150c18148190bf8152189c0e5fca |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:50 p.m.