As opposed to what many people might think, metaphor is not limited to similarity-based extensions of meanings of individual words. Instead, this phenomenon activates permanent mappings that reconceptualize one whole area of experience in terms of another. This article defends that even that CMT has produced important advancements in numerous fields of study such as philosophy, linguistics, cognitive science or artificial intelligence, there is still the need of a comprehensive corpus-based study of conceptual metaphor in order to empirically evaluate the CMT using real world linguistic data. With the objective of filling this gap in mind, this investigation has concentrated on the investigation of (1) how intuitive the conceptual metaphor explanation of linguistic metaphors is for human annotators and whether it is possible to consistently annotate interconceptual mappings; (2) what are the main difficulties that the annotators experience during the annotation process; (3) whether one conceptual metaphor is sufficient to explain a linguistic metaphor or whether a chain of conceptual metaphors is needed. This study represents a new, valuable dataset for linguistic, computational and cognitive experiments on metaphor.