Create a simple entity

  • Rversion finale: Australia
  • Mis à jour 12 mars 2026
  • 2 minutes de lecture

    • Create one or more simple entities from words in your utterance examples. An entity is an object of, or context for, an action.

    Avant de commencer

    • 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.

    Pourquoi et quand exécuter cette tâche

    Simple entities are words or phrases whose value can be extracted by your model. Simple entities are identified based on the context in which the entity is used in an utterance.

    For the following example procedure, you've already created an intent that's titled SubmitAccessRequest and you're creating a simple entity for the type of access the user is requesting.

    Procédure

    1. Navigate to All > NLU Workbench > Models.
      The Virtual Agent tab opens by default.
    2. Select the tab corresponding to your model's application, then the name of the model you want to add an entity to.
      For this example, you choose the NLU for Access Requests model.
    3. In the Build and train your model card, click View phase.
    4. In the intents tab, click the name of the intent.
      For this example, you click SubmitAccessRequest.
    5. Click a word in one of the utterances to bring up the entity window.
      For this example, click the word parking garage.
      Utterances tab of the intent details page with the entity window open.
    6. Click Create New Entity.
    7. In the Create a new entity screen, enter a name and select the Simple entity type.
      For this example, you enter buildingaccess for the Entity Name.
      Create a new entity window.
      Remarque :
      Select Model availability to make the entity available to every intent in the model. If you check the box, the entity shows in the Associated Entities tab.
    8. Click Save.
      The entity saves and the words in the utterance remain highlighted.

    Que faire ensuite

    Your utterances can reference a vocabulary source by using the @ handle. If you have a list of values that are defined in a vocabulary source, you can annotate the @ handle as a simple entity to extract it rather than repeating the utterance for all of the values. The referenced vocabulary source can be a table or a list. For example, the following image shows how you invoke a vocabulary source that lists various conference room names.

    Figure 1. Example utterance using a vocabulary source
    How to reference a vocabulary source from within an utterance.

    For more information, see NLU vocabulary.