Some products and features are in the process of being renamed. Generative playbook and flow features are also being migrated to a single consolidated console. See the details.
Stay organized with collections
Save and categorize content based on your preferences.
Entity types
are used to control how data from end-user input is extracted.
Conversational Agents (Dialogflow CX) provides predefined
system entities
that can match many common types of data.
For example, there are system entities for matching dates,
times, colors, email addresses, and so on.
You can also create your own
custom entities
for matching custom data.
For example,
you could define a vegetable entity
that can match the types of vegetables available
for purchase with a grocery store agent.
Entity terminology
The term entity is used in this documentation and in the Dialogflow CX console
to describe the general concept of entities.
When discussing entity details,
it's important to understand more specific terms:
Entity type:
Defines the type of information you want to extract from user input.
For example, vegetable could be the display name of an entity type.
Clicking Create from the Entity Types section
of the Dialogflow CX console creates an entity type.
When using the API,
the term entity type refers to the EntityType type.
Select a protocol and version for the EntityType reference:
(Optional) Description: Describes the purpose of the entity type, for
example "This entity is triggered when the user mentions a vegetable". If
you intend to use AI generation to auto-generate reference value synonyms,
this field will be used by the model to produce higher-quality results.
Entity entry:
For each entity type, there can be many entity entries. Each entity entry
provides a set of words or phrases that are considered equivalent, a
reference value in the first column and one or more synonyms to that
reference value in the second column. For example, if vegetable is an
entity type, you could define these entity entries:
Reference value
Synonyms
scallion
scallion, green onion
bell pepper
bell pepper, sweet pepper
carrot
carrot
potato
potato, tater, tuber
Instead of entering entity entries and synonyms manually, you can select
the Auto-generate __ syonyms per entity checkbox when you create a new
entity entry. The default value is 3 synonyms. The AI will generate synonyms
based on the reference value and entity type description and enter them in
the table. Please note that the synonyms list must also include the
original reference value in order to produce a match to that value.
When editing an entity type from the Dialogflow CX console, each row of the
display is an entity entry. When using the API,
the term entity entry refers to the
Entity type (EntityType.Entity or EntityType_Entity
for some client library languages).
Entity reference value and synonyms:
Some entity entries have multiple words or phrases
that are considered equivalent,
like the scallion in previous example.
For these entity entries, you provide one reference value
and one or more synonyms.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07 UTC."],[[["\u003cp\u003eEntity types control the extraction of data from user input in Conversational Agents (Dialogflow CX).\u003c/p\u003e\n"],["\u003cp\u003eDialogflow CX offers predefined system entities for common data types like dates and times, and allows the creation of custom entities.\u003c/p\u003e\n"],["\u003cp\u003eAn entity type defines the kind of information to be extracted, such as "vegetable" as a display name for an entity type.\u003c/p\u003e\n"],["\u003cp\u003eEntity entries within an entity type contain a reference value and a set of synonyms that are treated as equivalent in user input.\u003c/p\u003e\n"],["\u003cp\u003eDialogflow CX allows for the automatic generation of synonyms for entity reference values using AI, to simplify the process of defining entity entries.\u003c/p\u003e\n"]]],[],null,["# Entities\n\n*Entity types* are used to control how data from end-user input is extracted.\n\n\u003cbr /\u003e\n\nConversational Agents (Dialogflow CX) provides predefined\n[system entities](/dialogflow/cx/docs/concept/entity-system)\nthat can match many common types of data.\nFor example, there are system entities for matching dates,\ntimes, colors, email addresses, and so on.\nYou can also create your own\n[custom entities](/dialogflow/cx/docs/concept/entity-custom)\nfor matching custom data.\nFor example,\nyou could define a vegetable entity\nthat can match the types of vegetables available\nfor purchase with a grocery store agent.\n\nEntity terminology\n------------------\n\nThe term *entity* is used in this documentation and in the Dialogflow CX console\nto describe the general concept of entities.\nWhen discussing entity details,\nit's important to understand more specific terms:\n\n- **Entity type** :\n Defines the type of information you want to extract from user input.\n For example, *vegetable* could be the display name of an entity type.\n Clicking **Create** from the **Entity Types** section\n of the Dialogflow CX console creates an *entity type* .\n When using the API,\n the term *entity type* refers to the `EntityType` type.\n\n\n Go to the EntityType API reference\n\n **Select a protocol and version for the EntityType reference:**\n\n Close\n\n \u003cbr /\u003e\n\n- **(Optional) Description**: Describes the purpose of the entity type, for\n example \"This entity is triggered when the user mentions a vegetable\". If\n you intend to use AI generation to auto-generate reference value synonyms,\n this field will be used by the model to produce higher-quality results.\n\n- **Entity entry** :\n For each entity type, there can be many *entity entries* . Each entity entry\n provides a set of words or phrases that are considered equivalent, a\n *reference value* in the first column and one or more *synonyms* to that\n reference value in the second column. For example, if *vegetable* is an\n entity type, you could define these entity entries:\n\n Instead of entering entity entries and synonyms manually, you can select\n the **Auto-generate __ syonyms per entity** checkbox when you create a new\n entity entry. The default value is 3 synonyms. The AI will generate synonyms\n based on the reference value and entity type description and enter them in\n the table. Please note that the synonyms list must also include the\n original reference value in order to produce a match to that value.\n\n When editing an entity type from the Dialogflow CX console, each row of the\n display is an *entity entry* . When using the API,\n the term *entity entry* refers to the\n `Entity` type (`EntityType.Entity` or `EntityType_Entity`\n for some client library languages).\n- **Entity reference value and synonyms** :\n Some entity entries have multiple words or phrases\n that are considered equivalent,\n like the *scallion* in previous example.\n For these entity entries, you provide one *reference value*\n and one or more *synonyms*."]]
