Triple
T32733516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gated Recurrent Unit |
E837015
|
entity |
| Predicate | typicalActivationFunction |
P16017
|
FINISHED |
| Object | tanh |
—
|
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: tanh | Statement: [Gated Recurrent Unit, typicalActivationFunction, tanh]
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 (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_69f34935fb048190ad4967420581f835 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a037cad051c8190b28b354b89208574 |
completed | May 12, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_6a0379f0cbe481909b4b8fc6cbe297f0 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:11 a.m.