Triple
T8483211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WaveGlow |
E200567
|
entity |
| Predicate | advantageOverAutoregressiveModels |
P83526
|
FINISHED |
| Object | parallel sampling |
—
|
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: parallel sampling | Statement: [WaveGlow, advantageOverAutoregressiveModels, parallel sampling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: advantageOverAutoregressiveModels Context triple: [WaveGlow, advantageOverAutoregressiveModels, parallel sampling]
-
A.
hasLanguageModel
Indicates that an entity possesses, uses, or is associated with a particular language model.
-
B.
usesNeuralNetworks
Indicates that one entity employs neural network models or techniques as part of its functioning, processing, or decision-making.
-
C.
concurrentModel
Indicates that two or more processes, activities, or states occur or are valid at the same time, potentially interacting or overlapping in execution.
-
D.
zeroShotPrompting
Indicates that one entity elicits a response or behavior from another without using any task-specific examples, relying solely on general instructions or descriptions.
-
E.
trainerModel
Indicates that one entity serves as the trainer or training source for a model entity.
- F. None of above. chosen
Provenance (4 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_69ca831b17988190a1f3f3413d57b820 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe53845e881909eeb32863c7aa942 |
completed | March 31, 2026, 3:16 p.m. |
| PD | Predicate disambiguation | batch_69cbd107633c8190a36ba50e07876918 |
completed | March 31, 2026, 1:49 p.m. |
| PDg | Predicate description generation | batch_69cbe30c2d088190b4cb89adb4e88273 |
completed | March 31, 2026, 3:06 p.m. |
Created at: March 30, 2026, 6:12 p.m.