Table Of Contents


User Guide

First time using the AWS CLI? See the User Guide for help getting started.

Note: You are viewing the documentation for an older major version of the AWS CLI (version 1).

AWS CLI version 2, the latest major version of AWS CLI, is now stable and recommended for general use. To view this page for the AWS CLI version 2, click here. For more information see the AWS CLI version 2 installation instructions and migration guide.

[ aws . comprehend ]



Starts an asynchronous entity detection job for a collection of documents. Use the 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.

See also: AWS API Documentation

See 'aws help' for descriptions of global parameters.


--input-data-config <value>
--output-data-config <value>
--data-access-role-arn <value>
[--job-name <value>]
[--entity-recognizer-arn <value>]
--language-code <value>
[--client-request-token <value>]
[--volume-kms-key-id <value>]
[--vpc-config <value>]
[--cli-input-json <value>]
[--generate-cli-skeleton <value>]


--input-data-config (structure)

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

Shorthand Syntax:


JSON Syntax:

  "S3Uri": "string",

--output-data-config (structure)

Specifies where to send the output files.

Shorthand Syntax:


JSON Syntax:

  "S3Uri": "string",
  "KmsKeyId": "string"

--data-access-role-arn (string)

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 .

--job-name (string)

The identifier of the job.

--entity-recognizer-arn (string)

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.

--language-code (string)

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. If custom entities recognition is used, this parameter is ignored and the language used for training the model is used instead.

Possible values:

  • en
  • es
  • fr
  • de
  • it
  • pt
  • ar
  • hi
  • ja
  • ko
  • zh
  • zh-TW

--client-request-token (string)

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

--volume-kms-key-id (string)

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"

--vpc-config (structure)

Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your entity detection job. For more information, see Amazon VPC .

Shorthand Syntax:


JSON Syntax:

  "SecurityGroupIds": ["string", ...],
  "Subnets": ["string", ...]

--cli-input-json (string) Performs service operation based on the JSON string provided. The JSON string follows the format provided by --generate-cli-skeleton. If other arguments are provided on the command line, the CLI values will override the JSON-provided values. It is not possible to pass arbitrary binary values using a JSON-provided value as the string will be taken literally.

--generate-cli-skeleton (string) Prints a JSON skeleton to standard output without sending an API request. If provided with no value or the value input, prints a sample input JSON that can be used as an argument for --cli-input-json. If provided with the value output, it validates the command inputs and returns a sample output JSON for that command.

See 'aws help' for descriptions of global parameters.


JobId -> (string)

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

JobStatus -> (string)

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 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.