Gemini Nano
E490190
Gemini Nano is a lightweight, on-device variant of Google’s Gemini AI model designed to run efficiently on mobile and edge devices.
All labels observed (4)
| Label | Occurrences |
|---|---|
| Gemini Nano canonical | 2 |
| Gemini 1.0 in efficiency | 1 |
| Gemini 1.5 Nano | 1 |
| Gemini 2.0 Nano | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T5052787 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gemini Nano Context triple: [Google Gemini, hasVersion, Gemini Nano]
-
A.
Gemini SC-4
Gemini SC-4 was the NASA spacecraft used for the Gemini 4 mission, which carried astronauts James McDivitt and Edward White on the first American spacewalk in 1965.
-
B.
ArgoMoon CubeSat
ArgoMoon CubeSat is a small Italian-built spacecraft designed to demonstrate proximity operations and imaging capabilities in deep space during NASA’s Artemis I mission.
-
C.
Calliope mini
Calliope mini is a small educational microcontroller board designed to teach children and beginners programming and electronics through interactive projects.
-
D.
Nomos Alpha
Nomos Alpha is a groundbreaking solo cello composition by Iannis Xenakis, known for its complex mathematical structures and avant-garde sonic exploration.
-
E.
Nanocnide
Nanocnide is a little-known genus of flowering plants in the hemp family Cannabaceae, likely comprising herbaceous species related to nettles and hops.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gemini Nano Target entity description: Gemini Nano is a lightweight, on-device variant of Google’s Gemini AI model designed to run efficiently on mobile and edge devices.
-
A.
Gemini SC-4
Gemini SC-4 was the NASA spacecraft used for the Gemini 4 mission, which carried astronauts James McDivitt and Edward White on the first American spacewalk in 1965.
-
B.
ArgoMoon CubeSat
ArgoMoon CubeSat is a small Italian-built spacecraft designed to demonstrate proximity operations and imaging capabilities in deep space during NASA’s Artemis I mission.
-
C.
Calliope mini
Calliope mini is a small educational microcontroller board designed to teach children and beginners programming and electronics through interactive projects.
-
D.
Nomos Alpha
Nomos Alpha is a groundbreaking solo cello composition by Iannis Xenakis, known for its complex mathematical structures and avant-garde sonic exploration.
-
E.
Nanocnide
Nanocnide is a little-known genus of flowering plants in the hemp family Cannabaceae, likely comprising herbaceous species related to nettles and hops.
- F. None of above. chosen
Statements (32)
| Predicate | Object |
|---|---|
| instanceOf |
large language model
ⓘ
on-device AI model ⓘ |
| announcedBy | Google ⓘ |
| benefit |
better user data privacy compared to cloud-only models
ⓘ
improved responsiveness for AI features ⓘ reduced network dependency ⓘ |
| deployment | on-device runtime ⓘ |
| designedFor |
edge devices
ⓘ
mobile devices ⓘ on-device inference ⓘ resource-constrained environments ⓘ |
| developer |
Google
ⓘ
Google DeepMind ⓘ
linked to:
DeepMind
|
| distinguishedBy | smaller parameter count than cloud Gemini models ⓘ |
| feature |
lightweight architecture
ⓘ
low-latency inference ⓘ power-efficient operation ⓘ privacy-preserving on-device processing ⓘ |
| modelType | multimodal language model ⓘ |
| optimizedFor |
Android devices
ⓘ
on-device AI features in Android ⓘ |
| partOf | Gemini model family ⓘ |
| relatedTo |
Gemini Pro
ⓘ
Gemini Ultra ⓘ |
| supportsModality | text ⓘ |
| supportsTask |
code-related assistance
ⓘ
on-device assistant features ⓘ smart reply ⓘ text generation ⓘ text summarization ⓘ |
| usedIn |
Android system features
ⓘ
third-party Android apps ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Gemini Nano Description of subject: Gemini Nano is a lightweight, on-device variant of Google’s Gemini AI model designed to run efficiently on mobile and edge devices.
Referenced by (5)
Full triples — surface form annotated when it differs from this entity's canonical label.
linked to: Gemini Nano
linked to: Gemini Nano
linked to: Gemini Nano