Create a mapped entity

Create an entity mapped to a vocabulary source, or to a list of values you manually create for the entity. Mapped entities can help provide multiple values the model can use as context when interpreting utterances.

Before you begin

• Make sure that the NLU Workbench plugin, NLU Workbench - Core plugin, NLU Common Model plugin, and Predictive Intelligence plugin are all installed and activated on your instance.
• Create or use an existing NLU model for Virtual Agent or AI Search.
• Create or use an existing intent.
• Role required: nlu_editor, nlu_admin, or admin. The nlu_editor must be assigned to the model.

About this task

Mapped entities take the words of the utterance and extract value based on a designated source. The model uses the source when predicting the intent.

When you create a mapped entity, you have the following three options for the source.

• Manual list of values: Use this option to manually enter a list of values for the entity. For example, you could create a mapped entity named priority and map it to the word urgent in an utterance, then manually build a list for it with values of High, Medium, and Low.
• Table vocabulary source: Use this option if you have a ServiceNow table that has the values you're looking for. Mapping an entity to a table vocabulary source enables the entity to reference multiple values from the table. For example, use a @Location vocabulary source, where @Location has values for cities and countries.
• List vocabulary source: Use this option if you don't have a ServiceNow table that has the values you're looking for. For example, use a @mouse vocabulary source, where @mouse has values for various models of hand-held computer devices.

In this example procedure, you create a mapped entity for urgency.

Procedure

1. Navigate to All > NLU Workbench > Models.

   The Virtual Agent tab opens by default.

2. Select the tab for your model's application, then the name of your model.

3. On the model details page, select the Intents tab.

4. In the Intents section of the model, select the name of an intent.

   For this example procedure, you select #SubmitRequest.

5. In the Utterances tab, select a word in an utterance

   In this scenario, you select the word urgent in the utterance I have an urgent request.

6. Select Mapped entities.

7. Select Create New Entity.

1. On the form, configure the fields.

For this example procedure, use the following configurations:

-   **Entity Name**: `priority`
-   **Type**: Mapped
-   **Model availability**: Select the check box
-   **Source:** **Use this if you have a table or list to refer to where the actual values and values they're mapped to are stored**
-   **Mapped value for the entity**: `high, medium, low`.

1. Click Save.

   Result: Your mapped entity saves. The entity appears on the Associated entities tab. Now the model can leverage machine learning and use the values provided to identify possible values.

What to do next

You can create a mapped entity using a vocabulary source to use the values in the source as the mapped entity.

Related topics

Create a table vocabulary source

Create a list vocabulary source