linear_learner_multi_model_endpoint_inf_pipeline.ipynb failed CI

Link to the notebook:
https://github.com/aws/amazon-sagemaker-examples/blob/master/advanced_functionality/multi_model_linear_learner_home_value/linear_learner_multi_model_endpoint_inf_pipeline.ipynb

Error:

---------------------------------------------------------------------------
Exception encountered at "In [46]":
---------------------------------------------------------------------------
ClientError Traceback (most recent call last)
in
4 AssumeRolePolicyDocument=json.dumps(trust_policy),
5 Description=description,
----> 6 MaxSessionDuration=3600
7 )

/opt/conda/lib/python3.7/site-packages/botocore/client.py in _api_call(self, *args, **kwargs)
355 "%s() only accepts keyword arguments." % py_operation_name)
356 # The "self" in this sc

[...]

ClientError: An error occurred (AccessDenied) when calling the CreateRole operation: User: arn:aws:sts::521695447989:assumed-role/ProdBuildSystemStack-ReleaseBuildRoleFB326D49-QK8LUA2UI1IC/SageMaker is not authorized to perform: iam:CreateRole on resource: arn:aws:iam::521695447989:role/allow_invoke_ny_model_role2021-05-11-01-06-25

Open advanced_functionality/multi_model_linear_learner_home_value/linear_learner_multi_model_endpoint_inf_pipeline.ipynb and start at cell In [46], where the CreateRole call fails. Reproduce the CI run and inspect the reported iam:CreateRole denial; done means the notebook pipeline completes CI without this AccessDenied error.

Written by the indexing model from the issue text.