It is generally assumed that the" lexical component" of a grammar may be treated on the analogue of the syntactic and phonological components, as a device that pairs words with specifications of the things and classes of things that they can normally be used to refer to; if an item can be used to refer to more than one extension, then, it must be accorded more than one lexical entry. We begin by showing how these assumptions come to grief over the problems posed by the phenomenon of polysemy, when one word, like chicken, is used to refer at one time to a kind of bird and at another to a kind of meat. It is argued, first that the inclusion of multiple lexical entries leads to undesirable complications in the syntax, and second that pragmatic schemata that generate multiple uses must be independently available, since the same phenomena appear in ostensive reference. An account of" deferred ostension" is presented, in which it is shown why you can point at some things to identify others; this account is then extended to the multiple uses of" descriptive terms." We proceed to argue that with descriptions, there is no way to tell which of the uses of a word is specified by the rules of language, either in practice or in principle; the semantics/pragmatics distinction cannot be drawn.