ITA Controlled English (CE)
Summary
ITA Controlled English (CE) is a structured English language for defining human and machine-readable models, and the CE Store is an open-source environment by IBM for working with CE.
View Cached Full Text
Cached at: 09/04/26, 12:01 AM
ce-store/ce-store
Source: https://github.com/ce-store/ce-store
ITA Controlled English (CE)
Controlled English is a form of structured English that allows you to define models of concepts, their properities and relationships, that is both Human and machine readable.
The CE Store contains everything you need to get started with a Controlled English environment.
We are an IBM initiated open source organisation focused on providing an experimental research environment for the ITA Controlled English language.
Quick Example
A CE model contains all of the information about the data loaded into the CE Store. It is built from sentences which contain concepts and instances.
- A sentence always ends with a full stop.
- A concept defines a thing.
- An instance is a single occurrence of that concept/thing.
An example of a sentence that defines a concept in CE is as follows:
conceptualise a ~ planet ~ P that has the value M as ~ mass ~ and has the value R as ~ radius ~.
We can then define an instance of a planet called ‘Earth’ using another CE sentence:
there is a planet named 'Earth' that has '5.972 × 10^24' as mass and has 6371 as radius.
For more detailed examples you can go to the Tutorials section of the wiki or watch a video for a detailed overview with examples (22 mins 48 seconds).
Quick Guide
- Installation and Setup
- Usage
- Tutorials
- API
- Cheatsheet
- Command Syntax
- Hudson
- Other Projects
- Contributing
- License
Installation and Setup - Use CE in IBM Cloud
An easy way to get started with Controlled English is through IBM Cloud. You can sign up to IBM Cloud for free, and once you’ve got an account, clicking the button above will automatically deploy a Cloud-hosted instance of your very own CE Store.
Important Note: After deployment to IBM Cloud you will find your ce-store running in http://(your IBM Cloud url)/ce-store/ rather than in the root of the IBM Cloud url. Therefore, to access the ce-store via the engineering panel you would navigate to http://(your IBM Cloud url)/ce-store/ui/
Installation and Setup - Run CE on your own machine
Clone the code
git clone https://github.com/ce-store/ce-store
Using Apache Maven
Using Apache Maven, run the following command to start up the CE Store application using an embedded Tomcat server.
mvn install
mvn tomcat:run
The CE Store will be available at the following URL http://localhost:8080/ce-store
Using Docker
docker pull cestore/ce-store
docker run --rm -it -p 8080:8080 cestore/ce-store
Building With Docker
Use Apache Maven to build a WAR file for the project with the following command.
mvn package
This WAR file can be built into a Docker image with the command below.
docker build -t ce-store .
Then start the container from this image running locally.
docker run --rm -it -p 8080:8080 ce-store
The CE Store will be available at the following URL http://localhost:8080/ce-store
Using Vagrant
Requires Vagrant to be installed.
vagrant up
vagrant ssh
cd /vagrant
Then follow the steps in Using Apache Maven.
Usage
Engineering Panel
The Engineering Panel provides a simple web interface to the CE Store, enabling the user view the contents of the CE Store, to load new CE sentences, run queries agains the store, and more.
To open the Engineering Panel go to <SERVER>/ce-store/ui. It should look like this:

The engineering panel has four main areas:
- [Left] Model operations: CE models can be loaded and modified.
- [Right] Object pane: Contents of a CE store can be viewed.
- [Bottom] Messages: Errors will be reported here
- [Centre] Working area: Interactions with the model.
The CE Store comes with a sample set of CE sentences to build a model about medical data. The wiki includes a tutorial for using the Medicine model.
Contributing
Read about contributing here.
License
Licensed under the Apache License, Version 2.0
Similar Articles
CEAA: A Cognitive Embodied Agents Architecture for Interactive Computing Systems
This paper proposes CEAA, a modular cognitive architecture for embodied intelligent virtual agents that integrates high-level reasoning models with real-time embodied execution in interactive 3D environments.
Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models
CE3D++ enables flexible dialogue-driven 3D and 4D scene editing by decoupling 2D editing from 3D reconstruction via a Hash-Atlas network and using a large language model to autonomously invoke visual tools.
ISEE: Interactive Semantic Enrichment for Database Fields
This paper introduces ISEE, an interactive system that uses LLM-based agents to assess and collaboratively enrich the semantic quality of database field descriptions, reducing cognitive load and improving downstream tasks like entity linking.
Context Is Not Control, a source-boundary eval for LLMs
A paper introducing 'Context Is Not Control', an evaluation benchmark for assessing source-boundary failures in LLMs' use of controlled text-mediated evidence. Includes replication packages for open-weight and frontier API models.
Contrastive ESA: Human Evaluation of Multiple Translations at Once
Introduces Contrastive Error Span Annotation (cESA), a protocol for human evaluation of multiple translations simultaneously, reducing annotation time and noise compared to standard methods.
