I think you may be onto an interesting piece of this, but I do want to be precise about how the names here are identified (this is described carefully in the source / tools comment above. Note that syllabic count isn't a feature here).

I (personally) think it's interesting to identify names that can be sub-divided into standalone names. There's some complexity around whether names that can technically be subdivided (but we do not think about as compound names themselves) should be included. As an example that generated a lot of discussion in a previous version, think about something like "Elizabeth" that can technically be subdivided into the standalone names "Eliza" and "Beth", but we don't really think of as a compound name in the sense you describe.

I think you raise an interesting question that gets at what the central interpretation of the plot is; there's a question here about whether this strategy maps cleanly onto true compound names, and I think you're right that there are some we'd want to hand-edit (or otherwise identify) if that's the main goal. To me, it's a tricky thing to decide.