---
sourceDocument: Australia Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/pt-BR/intelligent-experiences

 Release :

    - australia

ft:locale :

    - pt-BR

ft:publication_title :

    - Australia Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Create an open-ended entity

# Create an open-ended entity {#ariaid-title1}

* Versão de lançamento: Australia
* 
* Atualizado 12 de mar. de 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 min. de leitura

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.

## Antes de Iniciar

* 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.
{#create-open-ended-entity__ul_shl_vvs_tgb}

## Por Que e Quando Desempenhar Esta Tarefa

Open-ended entities tell the model to focus on the context of the entity
rather than the entity itself. When you mark a word or phrase as open-ended, the
system skips the entity and predicts the intent from the context that precedes or
follows the entity in the utterance.

For example, in the utterance <kbd class="ph userinput">I want to order an iPhone</kbd>, you
annotate the words "an iPhone" as an open-ended entity. The model focuses on the
context, predicting the user wants to order something. Since there are numerous
things the user could want to order, naming all of them would be an unbearable task
for the model author.

Using an open-ended entity instead of a simple entity helps the model focus on the
rest of the utterance and not the entity. In the iPhone example, the entity itself
is less relevant; so you want the system to ignore it.  
In other scenarios you should use a simple entity, as there could be multiple intents where you shouldn't have the system ignore the entity.  
Nota:  
You can't annotate a vocabulary source (referenced by @vocab_source in an utterance) as an open ended entity. You can only annotate a vocabulary source as a simple entity or a mapped entity. For example, if the utterance is "I want to order a laptop", then the word "laptop" can be annotated as an open ended entity. However, if the utterance is "I want to order @laptop" where @laptop refers to a table vocabulary source or a list vocabulary source, it can't be annotated as an open ended entity.

For this example scenario, you've created an NLU model with
an intent for your users to order company merchandise.  
In the following example procedure, you create an entity from one of your utterances so the system can recognize it as open-ended and reusable in other NLU models in your instance.  
Nota:  
You can use only one open-ended entity per intent.

## Procedimento

1. Navigate to AllNLU WorkbenchModels.  
   The Virtual Agent tab opens by default.
2. Select the tab for your model's application, then select the name of your model.
3. On the Model details page, click Intents.
4. Select the name of the intent you want to add the entity to.  
   For this example, you select the #OrderMerch intent.
5. In the Utterances tab, select a word or phrase of one of the utterances to bring up the entities window.  
   For this example, you select a hoodie.  
   Figura 1. Entity window
6. Select Create New Entity
7. On the Create a new entity screen, configure the fields.  
   For this example, use the following configurations:
   * Entity Name: <kbd class="ph userinput">merch</kbd>
   * Type: Select Open-Ended

   {#create-open-ended-entity__ul_ry5_lyr_lkb}  
   Figura 2. Create entity
8. Select Save.  
   The merch open-ended entity is annotated in the Utterances
   section of your model's Intent screen. When you point to its name, you can
   see that it persists as a new entity in the annotation details. This entity
   is reusable in all other NLU models in your
   instance.  

## O que Fazer Depois

Train your model to save the entities. You can try your model to see if it interprets
the utterance based on the context of the entity, rather than the entity itself.  
For this example, you can test your model with a different merchandise item.

1. Select Try Model.
2. Enter <kbd class="ph userinput">I want to order a polo</kbd>.
3. Select Go.

{#create-open-ended-entity__ol_xyv_32b_ftb}

The model predicts the intent and shows that it used the merch entity
for the a polo value.
**Conceitos relacionados**   

* [Using regular expressions in entities](https://servicenow-prod.fluidtopics.net/3eVQ5ob2Vd4oT9hEE_sEDg "Learn how to use regular expressions in your NLU entities to establish patterns that help the system locate, match, and manage text.")  
**Tarefas relacionadas**   

* [Create a simple entity](https://servicenow-prod.fluidtopics.net/YoOMqKUSHjJk0a0vl77R9w "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/vawhhK8fYzS77AOSbXei1Q "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/~EzG0wJ9wuPajRnFU7YomA "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 a system-derived entity](https://servicenow-prod.fluidtopics.net/U3JDomZUv9a44VlRc4eZGg "Create a custom entity that's derived from a default system entity such as date, time, duration, or location.")
* [Import entities](https://servicenow-prod.fluidtopics.net/IoQj6KV7_TxWoBRJtoSiww "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.")