IBM Data & AI

 Welcome to the IBM Data & AI Ideas Portal for Clients! 

We welcome and appreciate your feedback on IBM Data & AI Products to help make them even better than they are today!
Before you submit an idea, please perform a search first as a similar idea may have already been reported in the portal.  If a related idea is not yet listed, please create a new idea and include with it a description which includes expected behavior as well as why having this feature would improve the service and how it would address your use case.
IBM Employees:
  • Our team welcomes any feedback  and suggestions you have for improving our offerings / products!  This forum allows us to connect your offering / product improvement ideas with IBM product and engineering teams.
  • If you have not registered on this portal please click on the following link and register.  To complete registration you will need to open the email you will receive from Aha to confirm your identity.
Additional Information:
  • The shorter URL for this site is:
  • To view our roadmaps:
  • Reminder: This is not the place to submit defects or support needs, please use normal support channel for these cases
  • Please do not use the Ideas Portal for reporting bugs - we ask that you report bugs or issues with the product by contacting IBM support.

Support WKS subtypes

When uploading a trained WKS model as machine learning enrichment, only entities are detected and indexed, but not subtypes (on WD for CP4D).

Please also consider supporting subtypes in the planned real-time NLP feature.

  • Tristan Hoffmann
  • Apr 2 2020
  • Future Consideration
Why is it useful?
Who would benefit from this IDEA? As a customer I expect WKS models to be fully supported. Especially when using enterprise search, the support of WKS subtypes and their use as filters would be a great benefit for me.
How should it work?
Idea Priority
Priority Justification
Customer Name
Submitting Organization
Submitter Tags
  • Attach files
  • Marcell Streile commented
    7 Apr 09:03am

    In oneWEX we had the entity sub-type information from WKS in the CAS, so we were able to use it with a bit of custom coding.

    Thats also what we need in WD on DP4D, a JSON enrichment result not just with WKS entity type but also with the entity sub-type.

    Same JSON structure as you get when using the WKS entity enrichment in WD on public cloud.

  • YUTAKA MORIYA commented
    7 Apr 04:58am
    We already implemented this mechanism successfully using oneWEX but are currently migrating to WD on CP4D.

    What do you mean "implemented" here?
    Do you use oneWEX function only or do you develop an external program? Could you elaborate it so we can understand the scope of the product function?


  • Tristan Hoffmann commented
    6 Apr 03:13pm

    Thanks for your reply!
    We're using subtypes basically as a classification. For example we have an entity that detects the fund aim, which can be something like "improve energy efficiency", "educate the workforce about first aid" or something like that. Obviously the covered text can only be evaluated by humans, but via subtypes we can already detect which categories of fund aim a certain program falls into (e.g. education, energy efficiency) and use that category to refine search results.

    We already implemented this mechanism successfully using oneWEX but are currently migrating to WD on CP4D.

  • Phil Anderson commented
    6 Apr 02:19pm

    Can you please describe how you use sub-types today, and why types wouldn't work for your use-case?

  • and 17 more

NOTICE TO EU RESIDENTS: per EU Data Protection Policy, if you wish to remove your personal information from the IBM ideas portal, please login to the ideas portal using your previously registered information then change your email to "anonymous@euprivacy.out" and first name to "anonymous" and last name to "anonymous". This will ensure that IBM will not send any emails to you about all idea submissions