Entity Node

​

Add the Node

1. Open the dialog task.
2. Add the Entity node. See Add a Node.
3. The Entity window opens with Component Properties selected by default.

​

Configure the Node

​

Component Properties

1. Enter a Name and Display Name. Entity names cannot include spaces.
2. Select an Entity Type from the dropdown. See Entity Types.
3. If the type supports it, enable Multi-item to allow multiple values separated by commas, semicolons, or “and”.
4. Under User Prompt, enter the prompt shown to the user (for example, Enter the Departure Date).
   • Click Manage for channel-specific prompts. See Prompt Editor.
   • Click Settings > enable Override for this instance to set an instance-specific prompt. Disabling the toggle deletes the override and restores the component-level prompt.
5. Under Error Prompts, review and modify default error messages.
   • Click Manage to edit. See User Prompts.
   • Enable Override for this instance for instance-specific error messages.
   • Enable Present Prompts in the Order of Retries to reorder error messages using drag handles.
6. Toggle Rephrase Responses to rewrite agent replies using AI based on conversation context and user emotion. See GenAI Features.
7. Under Redaction of PII Data, set how PII entity values appear in prompts and messages at runtime:
   • De-identify PII data — shows the redacted value.
   • Use the original value — shows the actual value (useful for user confirmation).
   These options affect only runtime display. PII data is always redacted in chat history and internal logs, regardless of this setting.
8. Enable Sensitive Entity to mask, redact, or replace sensitive input at the node level. Disabled by default. When enabled:
   • Check Transient Entity to clear the data on session close. Chat history shows data_purge instead of the value.
   • Click +Add Pattern to add a regex for identifying sensitive data (for example, [a-zA-Z]{3}[-]\d{4}).
   • Select how to display sensitive data to unauthorized users:
     • Redaction — replace with a unique random alphanumeric value.
     • Replacement — replace with a static value you define.
     • Mask with character — mask leading and trailing characters with + or #.
   See Redacting PII Data.
9. Under Variable Namespaces, associate namespaces to scope this node’s execution. Visible only when Variable Namespace is enabled for the agent. See Managing Namespace.

​

Instance Properties

​

User Input

​

User Input Correction (v7.3, String entities only)

​

Entity Extraction

• Do not reuse: Prevents this entity’s input from being reused to extract other entities.
• Entity Rules: Configure JSON-based validation rules. Click Add Rules and enter JSON. See Entity Rules.

​

Advanced Controls

​

User Input Flow

1. Valid value → entity populated; dialog continues.
2. Ambiguous value → platform shows an ambiguity resolution prompt.
3. Invalid input at the ambiguity prompt:
   • If valid for the entity type → used as-is; dialog continues.
   • If invalid and triggers an intent/FAQ/small talk → handles per Hold & Resume; entity is re-prompted when dialog resumes.
   • If invalid and no intent triggered → entity left blank; dialog continues from transitions.
4. Retry limit exceeded → triggers Behavior on Exceeding Retries. For child tasks set to End of Dialog, the parent task also terminates.

​

NLP Properties

1. Under Suggested Synonyms, enter synonyms for the entity and press Enter after each. See Managing Synonyms.
2. Under Suggested Patterns, click + Add Pattern to add extraction patterns. See Managing Patterns.
3. Under Manage Context > Context Output, define context tags set when this entity is populated.
4. Enable Auto emits the entity values captured to add entity values to the context object automatically. See Context Management.

​

IVR Properties

​

Connection Properties

​

Entity Types

​

Address

{ "AddressEntity": "200 E Main ST Phoenix AZ USA 85123" }

​

Airport

{
  "AirportEntity": {
    "IATA": "LHR",
    "AirportName": "London Heathrow Airport",
    "City": "London",
    "ICAO": "EGLL"
  }
}

​

Attachment

{ "AttachmentEntity": "send" }

​

City

{ "CityEntity": "New York" }

​

Color

{ "ColorEntity": "green" }

​

Company

{ "OrganizationEntity": "amazon" }

• A large corpus of known global companies, mapping name variants to a canonical name (for example, Amazon, Amazon.com, Amazon Inc → “amazon”).
• Any capitalized word followed by a legal suffix: Inc, Incorporated, Corp, Corporation, Group, Ltd, Limited, Co, Company, LP, LLP, LLLP, LLC, PLLC.

​

Composite

​

Country

{
  "CountryEntity": {
    "alpha3": "USA",
    "alpha2": "US",
    "localName": "United States of America",
    "shortName": "United States",
    "numericalCode": 840
  }
}

​

Currency

{ "CurrencyEntity": { "code": "SGD", "amount": 20 } }

​

Custom

​

Date

{ "DateEntity": "1982-04-13" }

​

Date Period

{ "DatePeriodEntity": { "from": "2024-11-05", "to": "2024-11-10" } }

​

Date Time

{ "DateEntity": "2017-10-10T18:00:00+05:30" }

​

Description

{ "Description": "text here" }

​

Email

{ "Email": "help@example.com" }

​

List of Items (enumerated)

• ambiguousEntityValues — array of ambiguous matches (title, value, synonym). Reset on re-prompt.
• synonymsUsed — synonym used to identify the matched item. Reset on re-prompt.

​

List of Items (lookup)

​

Static List

​

Remote List

{
  "inputData": {
    "input": ["get account"],
    "usedUp": ["0-x-x"],
    "isMultiItem": false
  }
}

1. Platform populates context.inputData and calls the service.
2. One value returned → assigned to entity.
3. Multiple values returned → platform extracts match from the list. No match → user selects from the list.
4. Ambiguous values → user selects one.
5. Multi-item entity → all valid values assigned; invalid values discarded.
6. Empty or malformed response → falls back to User Prompt.

​

Location

{
  "Location": {
    "formatted_address": "Las Vegas, NV, USA",
    "lat": 36.1699412,
    "lng": -115.1398296
  }
}

​

Number

{ "NumberEntity": 16 }

​

Person Name

{ "PersonName": "John Smith" }

​

Percentage

{ "PercentageEntity": 0.6 }

​

Phone Number

{ "PhoneNumber": "+4075551212" }

​

Quantity

{
  "Quantity": {
    "unit": "milliliter",
    "amount": 500,
    "type": "volume",
    "source": "500 ml"
  }
}

​

String

​

Time

{ "TimeEntity": "T06:00:00+05:30" }

​

Time Zone

{ "TimeZoneEntity": "-06:00" }

​

URL

{ "URLEntity": "www.kore.ai" }

​

Zip Code

{ "ZipcodeEntity": "32746" }

​

Entity Rules

context.entityRules.<entityName> = {
  "ruleName": "value"
}

context.entityRules.<compositeEntityName> = {
  <subentityName>: {
    "ruleName": "value"
  }
}

​

Generic Rules

{ "preConditions": ["isCustomerX"] }

{ "preConditions": ["( buy )"] }

​

String and Description Rules

{ "letters": 2 }

{ "letters": "5-8" }

​

Number Rules

{ "asString": true }

{ "digits": "3" }

{ "digits": "13-17" }

​

Currency Rules

{ "defaultCode": "NZD" }

{ "maxDigits": 3 }

{ "currencyCodes": ["USD", "INR", "NZD"] }

{ "ignoreOnlyCode": true }

​

Composite Entity Rules (Model Number)

• @AccountNumbers: Number entity with "digits": 8
• @AccountSuffix: String entity with "letters": 2

​

Person Name Rules

{ "disablePatterns": ["possessive"] }

{ "ignoreWords": ["review", "~prepositionList"] }

{ "negativePatterns": ["about *"] }

​

Company Rules

{ "ignoreWords": ["atm"] }

​

Date Rules

{ "range": {"from": "2020-01-01", "to": "today"} }

{ "referenceDate": "2020-07-09" }

{ "returnOnlyMonthYear": true }

​

Date Period Rules

​

Date Time Rules

​

Time Rules

​

City Rules

{ "ignoreWords": "Send" }

​

Zip Code Rules

{ "preferredCountries": ["GB"] }

​

Location Rules

​

List of Values (LoV) Rules

{ "ignoreLemmaWords": true }

• Input I need a ticket → Extracted: ticket
• Input I need tickets → Error: not a valid option

{ "ignoreWords": ["~size"] }

• Input I need extra large size t-shirt → Extracted: extra large size t-shirt (ignores “size” during matching)

​

List of Items (enum) Rules

{ "ownership": "include" }

{ "ownership": "exclude" }

{ "ownership": "include", "includeWords": "great" }

{ "noIndexMatch": "true" }