The mistake you are making is that you are conflating technical definitions used for regulating product labeling with the general understanding and preferences of consumers in how they relate product categories together.

Ideally, these would be closely aligned, but given that the former is a set of mutually exclusive category definitions bounded by precise quantitative variables, and the latter are overlapping clines that people make varied subjective judgments about, it's impossible to have perfect alignment, and edge cases like the ones you're discussing here will naturally proliferate.