Understanding Exclusive-OR predictions in Elman network

I have been reading Elman network paper, which can be found Here. in page 185, under Exclusive-OR section it was written as follows.

Notice that, given the temporal structure of this sequence, it is only sometimes possible to predict the next item correctly. When the network has received the first bit-1 in the example above-there is a 50% chance that the next bit will be a 1 (or a 0). When the network receives the second bit (0), however, it should then be possible to predict that the third will be the XOR, 1. When the fourth bit is presented, the fifth is not predictable. But from the fifth bit, the sixth can be predicted, and so on.

So, to give a context, author was explaining how we can use networks with memory to form a XOR Gate.

What i don't understand here is this sentence

"When the network receives the second bit (0),however, it should then be possible to predict that the third will be the XOR,1"

How can we be sure that the third element is 1, given second element is 0. And again, why can't we predict 4th element.