Triple
T31632338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NVIDIA GeForce RTX 4090 |
E807201
|
entity |
| Predicate | supportsDlss |
P207394
|
FINISHED |
| Object | DLSS 3 |
E41923
|
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: DLSS 3 | Statement: [NVIDIA GeForce RTX 4090, supportsDlss, DLSS 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsDlss Context triple: [NVIDIA GeForce RTX 4090, supportsDlss, DLSS 3]
-
A.
supportsDLSS
chosen
Indicates that one entity provides or is compatible with DLSS (Deep Learning Super Sampling) functionality for another entity.
-
B.
supportsDLSSVersion
Indicates that one entity provides compatibility with, or is capable of operating using, a specified version of NVIDIA's DLSS technology.
-
C.
supportsDLSSFrameGeneration
Indicates that one entity provides or enables DLSS frame generation functionality for another entity.
-
D.
supportsNvidiaReflex
Indicates that one entity provides compatibility with or functionality for NVIDIA Reflex technology in relation to another entity.
-
E.
supportsNVIDIALightning
Indicates that one entity provides compatibility with or functional backing for NVIDIA Lightning technology used by another entity.
- F. None of above.
Provenance (4 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_69f348d892948190915f8facacb9568c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a038156e0288190bc1f2efe9d7f2646 |
completed | May 12, 2026, 7:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2b79d68d448190b3c64dad67831108 |
completed | June 12, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_6a038094212881909d8f451fee75b2a2 |
completed | May 12, 2026, 7:33 p.m. |
Created at: April 30, 2026, 10:45 p.m.