Triple
T31067531
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NVIDIA Turing architecture |
E791717
|
entity |
| Predicate | firstConsumerLaunch |
P139992
|
FINISHED |
| Object | 2018-09 |
—
|
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: 2018-09 | Statement: [NVIDIA Turing architecture, firstConsumerLaunch, 2018-09]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstConsumerLaunch Context triple: [NVIDIA Turing architecture, firstConsumerLaunch, 2018-09]
-
A.
firstProductLaunch
chosen
Indicates that an entity is carrying out or associated with its initial product introduction to the market.
-
B.
firstLaunchMission
Indicates that a mission is the first launch associated with a particular object, program, or entity.
-
C.
launchedFirstUnit
Indicates that one entity initiated and deployed the first unit of something (e.g., product, system, or mission) before any others.
-
D.
firstModuleLaunch
Indicates the event or relationship where the initial module of a system, project, or mission is launched or activated for the first time.
-
E.
firstTestLaunch
Indicates that an entity’s initial test launch event occurs, marking the first time it is experimentally deployed or sent into operation.
- 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_69f224cc0c5c81908404f087bff92997 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a036f0569cc8190a8ac7f4e07145d15 |
completed | May 12, 2026, 6:18 p.m. |
| PD | Predicate disambiguation | batch_6a036c42cf2481908760c7d48b9fc001 |
completed | May 12, 2026, 6:06 p.m. |
Created at: April 29, 2026, 9:01 p.m.