Triple
T18205079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DeiT |
E435881
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | DeiT-Ti |
—
|
NE NERFINISHED |
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: DeiT-Ti | Statement: [DeiT, hasVariant, DeiT-Ti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DeiT-Ti Context triple: [DeiT, hasVariant, DeiT-Ti]
-
A.
DeiT
chosen
DeiT is a family of data-efficient vision transformer models designed for image classification with reduced training data requirements and strong performance.
-
B.
ViT
ViT (Vision Transformer) is a deep learning model architecture that applies the transformer framework to image recognition tasks by treating images as sequences of patches.
-
C.
Swin Transformer
Swin Transformer is a hierarchical vision transformer architecture that uses shifted windows for efficient and scalable image recognition and related computer vision tasks.
-
D.
BEiTModel
BEiTModel is a vision transformer-based image encoder that uses a BERT-style masked image modeling pretraining strategy for various computer vision tasks.
-
E.
DeepScale
DeepScale was an AI startup focused on efficient deep learning and computer vision models for resource-constrained devices, particularly in the automotive and embedded systems space.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e222831081908f7d5500424e3acb |
completed | April 19, 2026, 2:09 p.m. |
Created at: April 10, 2026, 10:32 a.m.