Amazon Comprehend
Developer Guide

StartEntitiesDetectionJob

Starts an asynchronous entity detection job for a collection of documents. Use the DescribeEntitiesDetectionJob operation to track the status of a job.

This API can be used for either standard entity detection or custom entity recognition. In order to be used for custom entity recognition, the optional EntityRecognizerArn must be used in order to provide access to the recognizer being used to detect the custom entity.

Request Syntax

{ "ClientRequestToken": "string", "DataAccessRoleArn": "string", "EntityRecognizerArn": "string", "InputDataConfig": { "InputFormat": "string", "S3Uri": "string" }, "JobName": "string", "LanguageCode": "string", "OutputDataConfig": { "KmsKeyId": "string", "S3Uri": "string" }, "VolumeKmsKeyId": "string" }

Request Parameters

For information about the parameters that are common to all actions, see Common Parameters.

The request accepts the following data in JSON format.

ClientRequestToken

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 64.

Pattern: ^[a-zA-Z0-9-]+$

Required: No

DataAccessRoleArn

The Amazon Resource Name (ARN) of the AWS Identity and Access Management (IAM) role that grants Amazon Comprehend read access to your input data. For more information, see https://docs.aws.amazon.com/comprehend/latest/dg/access-control-managing-permissions.html#auth-role-permissions.

Type: String

Length Constraints: Minimum length of 20. Maximum length of 2048.

Pattern: arn:aws(-[^:]+)?:iam::[0-9]{12}:role/.+

Required: Yes

EntityRecognizerArn

The Amazon Resource Name (ARN) that identifies the specific entity recognizer to be used by the StartEntitiesDetectionJob. This ARN is optional and is only used for a custom entity recognition job.

Type: String

Length Constraints: Maximum length of 256.

Pattern: arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:entity-recognizer/[a-zA-Z0-9](-*[a-zA-Z0-9])*

Required: No

InputDataConfig

Specifies the format and location of the input data for the job.

Type: InputDataConfig object

Required: Yes

JobName

The identifier of the job.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 256.

Pattern: ^([\p{L}\p{Z}\p{N}_.:/=+\-%@]*)$

Required: No

LanguageCode

The language of the input documents. All documents must be in the same language. You can specify any of the languages supported by Amazon Comprehend: English ("en"), Spanish ("es"), French ("fr"), German ("de"), Italian ("it"), or Portuguese ("pt"). If custom entities recognition is used, this parameter is ignored and the language used for training the model is used instead.

Type: String

Valid Values: en | es

Required: Yes

OutputDataConfig

Specifies where to send the output files.

Type: OutputDataConfig object

Required: Yes

VolumeKmsKeyId

ID for the AWS Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:

  • KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"

  • Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"

Type: String

Length Constraints: Maximum length of 2048.

Required: No

Response Syntax

{ "JobId": "string", "JobStatus": "string" }

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The following data is returned in JSON format by the service.

JobId

The identifier generated for the job. To get the status of job, use this identifier with the DescribeEntitiesDetectionJob operation.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 32.

Pattern: ^([\p{L}\p{Z}\p{N}_.:/=+\-%@]*)$

JobStatus

The status of the job.

  • SUBMITTED - The job has been received and is queued for processing.

  • IN_PROGRESS - Amazon Comprehend is processing the job.

  • COMPLETED - The job was successfully completed and the output is available.

  • FAILED - The job did not complete. To get details, use the DescribeEntitiesDetectionJob operation.

  • STOP_REQUESTED - Amazon Comprehend has received a stop request for the job and is processing the request.

  • STOPPED - The job was successfully stopped without completing.

Type: String

Valid Values: SUBMITTED | IN_PROGRESS | COMPLETED | FAILED | STOP_REQUESTED | STOPPED

Errors

For information about the errors that are common to all actions, see Common Errors.

InternalServerException

An internal server error occurred. Retry your request.

HTTP Status Code: 500

InvalidRequestException

The request is invalid.

HTTP Status Code: 400

KmsKeyValidationException

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

HTTP Status Code: 400

ResourceNotFoundException

The specified resource ARN was not found. Check the ARN and try your request again.

HTTP Status Code: 400

ResourceUnavailableException

The specified resource is not available. Check to see if the resource is in the TRAINED state and try your request again.

HTTP Status Code: 400

TooManyRequestsException

The number of requests exceeds the limit. Resubmit your request later.

HTTP Status Code: 400

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: