Here we will present work based on a corpus specially designed and elicited in order to provide data for the study of classifier function in Greek Sign Language (GSL). Data elicitation was based on presentation to informants of a series of stimuli which lead to utterances entailing the set of classifier functions met in the language. The whole set of video recorded data were annotated in order to provide an appropriate corpus for the investigation of classifier instantiations. Annotation work was complemented by the use of a search tool, external to the ELAN environment, that allows to create a data base of annotated video clips by exploiting the set of classification features used to annotate the video recorded data. Theoretical analysis of the so created linguistic data supported the formulation of a proposal for classifier behaviour which differentiates among three distinguished grammar functions based on the property of classifiers to act as semantic markers that create semantic classes of objects sharing common semantic features.