Could I use OpenNLP without machine learning?

I have a straightforward task of determining the sentence structure, specifically to identify if a sentence written in plain English is in the “present simple” tense and I want to write a small java program without using machine learning.

I know that I can use OpenNLP library for that, but it seems that library requires already trained model to check plain text.

Can I use OpenNLP library without machine-learning? I have heard about rule-based approach, could it help here?