JAX
E95194
JAX is a high-performance numerical computing library for Python that combines NumPy-like APIs with automatic differentiation and just-in-time compilation, widely used for machine learning and scientific computing.
All labels observed (2)
| Label | Occurrences |
|---|---|
| JAX canonical | 11 |
| JAX (stylized) | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T805164 — 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: JAX Context triple: [OpenAI Gym, compatibleWith, JAX]
-
A.
JAXPORT
JAXPORT is the public seaport authority for Jacksonville, Florida, serving as a major U.S. hub for container, automobile, and bulk cargo shipping.
-
B.
IJ Bay
IJ Bay is a body of water in the Netherlands that forms a key waterfront and harbor area for the city of Amsterdam.
-
C.
Dix
Dix is the surname of Dorothea Dix, the 19th-century American social reformer known for her pioneering work in mental health care and prison reform.
-
D.
Savannah
Savannah is a historic coastal city in the U.S. state of Georgia, renowned for its well-preserved architecture, cobblestone squares, and rich Southern cultural heritage.
-
E.
Arcot
Arcot is a historic town in the Indian state of Tamil Nadu that served as an important political and military center, especially under the Nawabs of the Carnatic during the 18th century.
- 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: JAX Target entity description: JAX is a high-performance numerical computing library for Python that combines NumPy-like APIs with automatic differentiation and just-in-time compilation, widely used for machine learning and scientific computing.
-
A.
JAXPORT
JAXPORT is the public seaport authority for Jacksonville, Florida, serving as a major U.S. hub for container, automobile, and bulk cargo shipping.
-
B.
IJ Bay
IJ Bay is a body of water in the Netherlands that forms a key waterfront and harbor area for the city of Amsterdam.
-
C.
Dix
Dix is the surname of Dorothea Dix, the 19th-century American social reformer known for her pioneering work in mental health care and prison reform.
-
D.
Savannah
Savannah is a historic coastal city in the U.S. state of Georgia, renowned for its well-preserved architecture, cobblestone squares, and rich Southern cultural heritage.
-
E.
Arcot
Arcot is a historic town in the Indian state of Tamil Nadu that served as an important political and military center, especially under the Nawabs of the Carnatic during the 18th century.
- F. None of above. chosen
Statements (57)
| Predicate | Object |
|---|---|
| instanceOf |
Python library
ⓘ
numerical computing library ⓘ open-source software ⓘ |
| compatibleWith |
Flax
ⓘ
Haiku ⓘ NumPy ⓘ Optax ⓘ Python scientific stack ⓘ
surface form:
SciPy ecosystem
TensorFlow Probability (JAX backend) ⓘ |
| developedBy |
Google
ⓘ
Google Research ⓘ |
| documentation |
https://jax.readthedocs.io
ⓘ
https://jax.readthedocs.io/en/latest/ ⓘ |
| hasAPIStyle | NumPy-like API ⓘ |
| hasComponent |
jax.experimental
ⓘ
jax.lax ⓘ NumPy ⓘ
surface form:
jax.numpy
jax.random ⓘ |
| implements |
NumPy
ⓘ
surface form:
NumPy API subset
XLA-backed array operations ⓘ automatic differentiation primitives ⓘ |
| license | Apache License 2.0 ⓘ |
| programmingLanguage | Python ⓘ |
| repository | https://github.com/google/jax ⓘ |
| supportsFeature |
GPU acceleration
ⓘ
TPU acceleration ⓘ XLA compilation ⓘ automatic differentiation ⓘ custom gradients ⓘ differentiation of Python functions ⓘ forward-mode automatic differentiation ⓘ functional transformations ⓘ grad-based optimization ⓘ higher-order differentiation ⓘ jit compilation decorator ⓘ just-in-time compilation ⓘ just-in-time compiled NumPy operations ⓘ just-in-time compiled control flow ⓘ parallelization ⓘ pmap parallel mapping ⓘ random number generation ⓘ reverse-mode automatic differentiation ⓘ vectorization ⓘ vmap vectorized mapping ⓘ |
| targetUser |
engineers
ⓘ
machine learning researchers ⓘ scientists ⓘ |
| usedFor |
deep learning
ⓘ
differentiable programming ⓘ large-scale linear algebra ⓘ machine learning research ⓘ neural network training ⓘ numerical optimization ⓘ probabilistic modeling ⓘ scientific computing ⓘ simulation-based inference ⓘ |
| writtenIn | Python ⓘ |
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: JAX Description of subject: JAX is a high-performance numerical computing library for Python that combines NumPy-like APIs with automatic differentiation and just-in-time compilation, widely used for machine learning and scientific computing.
Referenced by (12)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
JAX (stylized)