Triple
T18204716
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OPT |
E435873
|
entity |
| Predicate | supportsInferencePrecision |
P60855
|
FINISHED |
| Object | FP16 |
—
|
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: FP16 | Statement: [OPT, supportsInferencePrecision, FP16]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsInferencePrecision Context triple: [OPT, supportsInferencePrecision, FP16]
-
A.
supportsInferenceOf
Indicates that one entity provides a logical basis or justification for concluding or deriving another entity.
-
B.
supportsQuantization
Indicates that one entity is capable of operating with, or is compatible with, quantized representations or computations of another entity.
-
C.
supportsNeuralNetworkAcceleration
Indicates that one entity provides hardware or software capabilities that enhance the speed or efficiency of neural network computations for another entity.
-
D.
supportsArbitraryPrecisionArithmetic
Indicates that the subject system or component can perform arithmetic operations with numbers of virtually unlimited size and precision, beyond fixed hardware-imposed limits.
-
E.
supportsPrecisionLevels
chosen
Indicates that one entity is capable of operating at, or accommodating, multiple specified levels of precision in relation to another entity or process.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e222831081908f7d5500424e3acb |
completed | April 19, 2026, 2:09 p.m. |
| PD | Predicate disambiguation | batch_69e4332155d88190b106d0dceb4554af |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:32 a.m.