Triple
T1180437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | deep feedforward networks |
E25122
|
entity |
| Predicate | regularizedBy |
P16020
|
FINISHED |
| Object | weight decay |
—
|
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: weight decay | Statement: [deep feedforward networks, regularizedBy, weight decay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regularizedBy Context triple: [deep feedforward networks, regularizedBy, weight decay]
-
A.
regularization
chosen
Indicates the application of a constraint or penalty to a model or function to prevent overfitting and encourage simpler, more generalizable behavior.
-
B.
regulatesWith
Indicates that one entity controls, modulates, or influences the activity, state, or behavior of another entity through some regulatory mechanism or interaction.
-
C.
stabilizedBy
Indicates that an entity’s state, structure, or behavior is made more steady, secure, or resistant to change through the influence or support of another entity.
-
D.
regulatoryType
Indicates the specific kind or category of regulatory control, rule, or oversight that applies in the given relationship.
-
E.
regulatesUse
Indicates that one entity controls, governs, or sets rules for how another entity may be used.
- 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_69a494267b4c819088c97a59182bf56a |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd32c5f48190b4e2d39fa052cbb7 |
completed | March 1, 2026, 10:26 p.m. |
| PD | Predicate disambiguation | batch_69a4bb59ca6c81908597a81646674aaa |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.