This paper is a contribution to a long-standing debate between constructionist, lexicalist, and emergentist schools of thought related to the question of what determines the category of lexically ambiguous words whose meanings belong to different syntactic categories (e.g., duck, walk). In the lexicalist view part-of-speech information is stored in the mental lexicon. According to the syntax-first (or constructionist) view, the ambiguous word is assigned to the syntactic category NOUN or VERB solely on the basis of the morphosyntactic frame in which it occurs irrespective of its meaning. In contrast, the emergentist view assumes an interaction of many constraints (semantic and syntactic) whereby semantic constraints are weaker than syntactic constraints in the resolution of word class ambiguities because while semantic context only favors one of the meanings of ambiguous words but does not exclude the competitors, syntactic context supports one meaning of an ambiguous word by ruling out its alternative interpretation. We intend to provide an overview of recent psycholinguistic studies focusing on the processing of word-class ambiguities in order to show that the syntax-first approach is too restrictive while the emergentist view is too permissive. What seems to be at issue is that when grammatical category-ambiguous words are processed, it is not that all constraints are available at the same time and they compete but rather different sources of information can be predicted to affect the process of lexical disambiguation at different stages during processing.