The LibraryThing is the home of OverCat, a collection of 32 million library records.
It is a nifty illustration of re-using identifiers, not re-inventing them.
I put in an ISBN, for example, and the system searches for that work. It does not ask me to create a “cool” URI for it.
It also demonstrates some of the characteristics of a topic map in that it does return multiple matches for all the libraries that hold a work, but only one. (You can still view the other records as well.)
I am not sure I have the time to enter, even by ISBN, all the books that line the walls of my office but maybe I will start with the new ones as they come in and the older ones as I use them. The result is a catalog of my books, but more importantly, additional information about those works entered by others.
Maybe that could be a marketing pitch for topic maps? That topic maps enable users to coordinate their information with others, without prior agreement. Sort of like asking for a ride to town and at the same time, someone in a particular area says they are going to town but need to share gas expenses. (Treating a circumference around a set of geographic coordinates as a subject. Users neither know nor care about the details, just expressing their needs.)