Triple
T29938080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GeForce3 |
E760422
|
entity |
| Predicate | coreClockRange |
P83979
|
FINISHED |
| Object | approximately 175–240 MHz depending on model |
—
|
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: approximately 175–240 MHz depending on model | Statement: [GeForce3, coreClockRange, approximately 175–240 MHz depending on model]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coreClockRange Context triple: [GeForce3, coreClockRange, approximately 175–240 MHz depending on model]
-
A.
minClockSpeed
Indicates the minimum operating clock speed required or supported for a given hardware component or system.
-
B.
clockSpeed
Indicates the operating frequency at which a clock-driven component (such as a processor) performs its cycles or operations over time.
-
C.
hasClockSpeed
Indicates that an entity (typically a processor or device) operates at a specified clock frequency or speed.
-
D.
operatingFrequencyApproximate
chosen
Indicates an approximate or estimated operating frequency at which an entity functions or is designed to function.
-
E.
coreRange
Indicates the primary spatial or temporal extent within which an entity, phenomenon, or relationship is predominantly present or valid.
- 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_69f22463f3648190a603c3ff305c660b |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f677d7ab2c8190a26f161c559ed05b |
completed | May 2, 2026, 10:16 p.m. |
| PD | Predicate disambiguation | batch_69f673c4abec8190bc2379e66f4af0a9 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 6:21 p.m.