---
sourceDocument: Xanadu Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/xanadu/intelligent-experiences

 Release :

    - xanadu

ft:locale :

    - en-US

ft:publication_title :

    - Xanadu Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Create a system-derived entity

# Create a system-derived entity {#ariaid-title1}

* Release version: Xanadu
* 
* Updated August 1, 2024
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read

Create a custom entity that's derived from a default system entity such as date, time, duration, or location.

## 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.](https://servicenow-prod.fluidtopics.net/rCLbf7GXrT3OPe5NypV1Iw "Activate the following plugins to activate the NLU Workbench.")
* [Create or use](https://servicenow-prod.fluidtopics.net/EN~zZkL5GYkqAEESELkXtQ "Creating models is the first step to taking advantage of Natural Language Understanding (NLU) in your instances. Create models for Virtual Agent and AI Search in the NLU Workbench.") an existing NLU model for Virtual Agent or AI Search.
* [Create or use an existing intent.](https://servicenow-prod.fluidtopics.net/Bmua__OOiVxVBdTRg4Bb2w "Create an intent for your Natural Language Understanding (NLU) model. Intents provide your model with a system action to perform when it receives user input.")
* Role required: nlu_editor, nlu_admin, or admin. The nlu_editor must be assigned to the model.
{#create-system-derived-entity__ul_shl_vvs_tgb}

## About this task

System entities are pre-built in your ServiceNow instance by default, and appear on the Entities section of the Model screen. These entities, such as DATE, TIME, and DATE_TIME, are enabled by default.
You can disable and re-enable them if needed by clicking Enable.

System-derived entities extend your system entities, providing more context. For example, your model already understands date formats thanks to the system entity DATE. However, you can create
system-derived entities, such as startdate and enddate, to extract more information from user utterances regarding dates.

For the following example scenario, you're creating a model for booking flights, cars, hotels, and events. You want your intent #FlightBooking to interpret utterances with your users flight requests. Your model
contains the system entity LOCATION, but flight plans usually involve two locations.

In this example procedure, you create two system-derived entities to gather the departure and arrival locations of the flight.

## Procedure

1. Navigate to AllNLU WorkbenchModels.  
   The Virtual Agent tab opens by default.
2. Select the tab for your model's application, then the name of your model.
3. In the model details page, select Intents.
4. Select the name of the intent.  
   For this example, you select the #FlightBooking intent.
5. On the Utterances tab, select a word or phrase from one of the utterances.  
   In this example scenario, you have an example utterances <kbd class="ph userinput">book a flight from San Diego to San Francisco</kbd>. For this step, click from San Diego.
6. Select Create New Entity.
7. In the Create a new entity screen, configure the fields.  
   For this example, use these configurations.
   * Entity Name: Enter <kbd class="ph userinput">FromLocation</kbd>
   * Type: Select System-derived
   * Model Availability: Select this check box if you want this entity to be included in all intents in your model
   * Parent Entity: Select LOCATION
   {#create-system-derived-entity__ul_ry5_lyr_lkb}
8. Select Save.
9. On the same utterance, select another word or phrase.  
   In this example scenario, you click to San Francisco.
10. Select Create New Entity.  
    For this example, use these configurations.
    * Entity Name: Enter <kbd class="ph userinput">ToLocation</kbd>
    * Type: Select System-derived
    * Model Availability: Select this check box if you want this entity to be included in all intents in your model
    * Parent Entity: Select LOCATION
    {#create-system-derived-entity__ul_ogj_nxb_jsb}
11. Select Save.  
    Result: Your two system-derived entities appear in the entity window.

## What to do next

Train your model to save the entities. You can try your model to see if it recognizes and interprets variations of the entities that you created.  
For this example, you can test your model with a different departure and arrival location.

1. Select Try model.
2. Enter <kbd class="ph userinput">book a flight from Dallas to San Jose</kbd>.
3. Select Go.

{#create-system-derived-entity__ol_mxn_dzb_jsb} Figure 1. Intents details page with the test panel The model predicts the intent, showing the entities it used to determine the values. Notice how it uses both the system entity and system-derived entity when predicting.
**Related concepts**   

* [Using regular expressions in entities](https://servicenow-prod.fluidtopics.net/MLF7GQKcQp5lQTgeBdhGfw "Learn how to use regular expressions in your NLU entities to establish patterns that help the system locate, match, and manage text.")  
**Related tasks**   

* [Create a simple entity](https://servicenow-prod.fluidtopics.net/N~5DJDKjarceXuhwMKE6fg "Create one or more simple entities from words in your utterance examples. An entity is an object of, or context for, an action.")
* [Create a mapped entity](https://servicenow-prod.fluidtopics.net/L36lfvGw3Fx2eblSAc6lRA "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.")
* [Create a pattern entity](https://servicenow-prod.fluidtopics.net/R06p7nAAw5pbg~ybFCp32Q "Create a pattern entity from a word or phrase with repeatable patterns, such as email addresses and phone numbers. These patterns help the system to recognize similar utterances based on the patterns.")
* [Create an open-ended entity](https://servicenow-prod.fluidtopics.net/ZSZ60xAPMEW~bNeORY2HfA "Use an open-ended entity when you want to improve intent prediction accuracy. Open-ended entities help your model focus on the context of the utterances.")
* [Import entities](https://servicenow-prod.fluidtopics.net/iz1K~UJviKCvsN2yRoYoCQ "Reuse entities that you have created across your other Natural Language Understanding (NLU) models. Importing entities saves time and helps improve the intents in your model.")

*[\>]: and then