Combining "expert-assigned labels" and "real-observed labels"?

Combining expert-assigned labels and real-observed labels?

That is, if I have a data set, where it's possible to have labels that are true observations and also labels that are the expert strongly believes that these features should result in this label.

Then how should these be combined?

Particularly, these do give different information, but they also contain, possibly, different problems.

Real-observed labels are assumed to be or are true.

However, they might not always exist, but instead there may exist an expert prediction that these features could lead to a label. The informativeness of these expert predictions may be very comparable to real-observed labels, when one lacks a real observation.

But should these be weighted differently or the same for example?