PLEASE NOTE: UiPath Communications Mining's Knowledge Base has been fully migrated to UiPath Docs. Please navigate to equivalent articles in UiPath Docs (here) for up to date guidance, as this site will no longer be updated and maintained.

Knowledge Base

Model Training & Maintenance

Guides on how to create, improve and maintain Models in Communications Mining, using platform features such as Discover, Explore and Validation

Enabling, disabling, updating and creating entities

User permissions required: 'View Sources' AND 'Modify Datasets' OR 'Datasets Admin'


Enabling entities on a new dataset


To enable entities on a new dataset that you want to create, you simply need to select them during the setup process.


Click the + button in the box shown below and you will be presented with a dropdown menu of all of the entities that you are able to enable for that dataset. Simply click all of the entities you want to enable before creating the dataset. If you add any in error, you can click the ‘X’ icon next to the entity name to remove it.


To understand more about how to create a new dataset, see here.



Create new dataset modal

Enabling, updating, and disabling entities on an existing dataset

If you want to enable, update or disable entities for an existing dataset, you can do so from the settings tab on the top navigation bar, and then selecting the 'Labels & Entities' tab.




 Settings > Labels & Entities tab 


Enabling entities:


To enable existing entities, click inside the 'Entities' box, and select the entities you want to enable from the drop down menu. Once you're happy with your selections, click 'Update Entities' (as shown below).

These entities will have their settings pre-selected for you. You can then update them, including making them trainable, as shown below. 


Entity section of Labels & Entities tab


Updating entities:

To update an enabled entity, click the entity in the entity box as shown in the above images and the 'Edit entity' modal (below) will appear.

Here you can update the base entity, the title of the entity and the API name (these concepts are described in detail below), as well as making the entity 'trainable'.

If you have previously reviewed entities for an entity kind that was not set to 'trainable', this information is still stored. 



Edit entity modal



Disabling entities:

To remove any selected entities, simply click the 'X' icon next to the entity name, and then click 'Update Entities'.

Please Note: If you remove an entity and click 'Update Entities', this will also remove the training data for that entity for this dataset. If you chose to re-enable the entity, you will need to train it again.

If you make a mistake while updating the entities, click 'Reset' before you click 'Update Entities' and your changes will not be applied.

Creating new entities


The above sections have covered how to enable and update existing pre-trained entities for both new and existing datasets. In each instance, for either a new or existing dataset, you can also create new entities.

Newly created entities can be based on an existing pre-trained entity or can be trained from scratch (like a new label).


You can do this by clicking the '+' icon in the entity box, either in the 'Create dataset' flow or in the dataset settings page (as shown above).


This will bring up the 'Add a new entity' modal as shown below.


Here you can set the entity base, title, and API name, as well as selecting whether the entity is trainable or not (these can be updated later as shown above).

When you've filled in each of the fields (explained below), simply click 'Create'.




Create new entity modal


Entity base


  • This will serve as the initial state for your new entity, and the dropdown will contain a list of all the pre-trained entities available to you
    • For example, if you select 'Date' as your base entity, all of the entities predicted for this kind will be dates, and you could then train the platform to only recognise specific dates
  • If you want to train an entity entirely from scratch, you can select  'None - Train from scratch', and then you essentially start with a blank canvas when training the entity. The platform's predictions for this entity will be entirely based on the training examples you provide

Entity title

  •  The entity title is the name of the entity that will appear in the UI of the platform


API name


  • The API name of the entity is what will be returned via the API when it provides predictions for verbatims
  • The API name cannot contain any spaces or punctuation except for dash  ( - ) and underscore ( _ )


Previous: Which pre-trained entities are available?   |   Next: Entity filtering 

Did you find it helpful? Yes No

Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.


View all