I'm at a loss as to how https://english.stackexchange.com/questions/44935/grammar-of-over-in-the-accident-was-already-over-when-we-arrived could be deemed unworthy of further consideration. Could anyone please explain what I'm missing?
The statement This question is too basic; it can be definitively and permanently answered by a single link to a standard internet reference source designed specifically to find that type of information. can arguably never be true, as English is a language that develops over time.
In many non-trivial cases, one may find incompatible 'definitive' answers by carefully selecting or just happening upon different 'standard internet reference sources designed specifically to provide that type of information'.
In the case of this sense of over, for instance, at thefreedictionary.com, the two (usually excellent) dictionaries give contradictory analyses:
14. At an end: Summer is over.
The American Heritage® Dictionary of the English Language, Fourth Edition copyright ©2000 by Houghton Mifflin Company. Updated in 2009.
adj (postpositive) finished; no longer in progress: is the concert over yet?
Collins English Dictionary – Complete and Unabridged © HarperCollins Publishers 1991, 1994, 1998, 2000, 2003
So, do we toss a coin? Stick with the first reasonably authoritative-looking source we happen upon? Look for a ranking order of possible sources? Look for a ranking order of ranking orders?
(With regard to the original question, Collins probably has the correct analysis here: the structure must be regarded as copular; over cannot modify be. However, as with former in say a former President, we have here a situation where the 'adjective' doesn't really truly modify the noun it is apparently associated with. A former President is not a President who is former, and if Summer is over, we are not left with an over Summer. The words 'former' and 'over' refer to former states / the end of those states. At the moment, words that perform this sort of role are loosely classed as 'peripheral adjectives', or perhaps better as 'non-semantically-predicative adjectives' (see Elizabeth Coppock at Google Books).
Oh, and the above link is to the best article on the subject that I've found in 10 years - but perhaps that's common knowledge?