Triple
T3507204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MNIST |
E74103
|
entity |
| Predicate | commonModelType |
P18973
|
FINISHED |
| Object | convolutional neural network |
—
|
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: convolutional neural network | Statement: [MNIST, commonModelType, convolutional neural network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonModelType Context triple: [MNIST, commonModelType, convolutional neural network]
-
A.
possibleModel
Indicates that one entity can serve as a potential or candidate model or template for another entity.
-
B.
typicalCoreType
chosen
Indicates that something is a standard or characteristic core type within a given classification or system.
-
C.
useOfModel
Indicates that one entity employs, applies, or relies on a particular model for a specific purpose or task.
-
D.
dataModel
Indicates a relationship where an entity defines, uses, or is structured according to a specific data model or schema.
-
E.
metadataType
Indicates that one entity specifies the kind or category of metadata associated with another entity.
- 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_69ad85ce7a9c81909ddc5cf0cb67a6e3 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbbf52bd8819085a2ac5f48cc5c68 |
completed | March 8, 2026, 6:12 p.m. |
| PD | Predicate disambiguation | batch_69adae0e770481908528fa35eda53003 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:18 p.m.