Your question is Approach NER or Topic Modeling. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
You are working on an NLP system that needs to extract structure from unstructured text or discover themes in a document collection. Depending on the use case, you may need a supervised sequence labeling approach or an unsupervised topic discovery workflow.
How do you approach named entity recognition or topic modeling?