Triple
T29108372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Differentiable Neural Computers |
E736824
|
entity |
| Predicate | typicalControllerImplementation |
P74636
|
FINISHED |
| Object | LSTM |
—
|
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: LSTM | Statement: [Differentiable Neural Computers, typicalControllerImplementation, LSTM]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalControllerImplementation Context triple: [Differentiable Neural Computers, typicalControllerImplementation, LSTM]
-
A.
typicalControllerType
Indicates the usual or most common type of controller associated with, or used to operate, a given entity.
-
B.
typicalFunctionClass
Indicates that something belongs to the usual or characteristic functional category associated with it.
-
C.
usesController
Indicates that one entity operates, manages, or interacts with another entity through a controller component or mechanism.
-
D.
exampleImplementation
chosen
Indicates that one entity serves as a concrete, illustrative implementation or instance of another, more general concept, design, or specification.
-
E.
typicalBaseClass
Indicates that one class is the usual or standard superclass (base class) from which another class is typically derived.
- 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_6a017a360f088190acd5933aa353e763 |
completed | May 11, 2026, 6:41 a.m. |
| PD | Predicate disambiguation | batch_6a0179d3f78c8190b1d2e8829619fa54 |
completed | May 11, 2026, 6:40 a.m. |
Created at: April 28, 2026, 11:17 a.m.