Triple
T32733516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gated Recurrent Unit |
E837015
|
entity |
| Predicate | typicalActivationFunction |
—
|
GENERATED |
| Object | tanh |
—
|
UNRECOGNIZED GENERATED |
How this triple was built (1 step)
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.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalActivationFunction Context triple: [Gated Recurrent Unit, typicalActivationFunction, tanh]
-
A.
activationFunction
chosen
Indicates the specific mathematical transformation applied to a neuron's input to produce its output in a computational or neural model.
-
B.
typicalFunction
Indicates that something serves as the usual or characteristic function or role of an entity.
-
C.
typeOfNonlinearity
Indicates the specific kind or form of nonlinearity that characterizes how one entity behaves or responds in relation to another.
-
D.
typicalFunctionClass
Indicates that something belongs to the usual or characteristic functional category associated with it.
-
E.
activationNetwork
Indicates that one entity initiates, enhances, or enables the functional activity of another entity within a connected system or pathway.
- F. None of above.
Provenance (1 batch)
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_69f34935fb048190ad4967420581f835 |
completed | April 30, 2026, 12:21 p.m. |
Created at: May 1, 2026, 1:11 a.m.