Proailurus |
Plesictis is an example here. It looked, so far as we can tell, rather like a polecat and was about the same size, so for much of the 20th century it was thought to be an early example of a mustelid, albeit one no more closely related to actual polecats than, say, badgers or otters are. More modern analyses are more circumspect; it may look like a mustelid in some respects, but it probably lived before those animals diverged from the raccoons and so can't be quite either. Palaeogale, which looked rather similar and was also originally assumed to be a mustelid, in fact turns out to be more related to cats and mongooses, but probably so far down the family tree that it's not yet possible to say much more than that.