Service composition can be considered as a Linked Data model due to the way that each one of the services that make up the composition is structured. For doing this, a service composer is required in order to evaluate the input and output data of various web-distributed services for linking them. These links can be analyzed from a quality perspective in which a service may fail when it does not fulfill the requirements that satisfy the linking conditions. Therefore, these conditions are analyzed from two points of view: 1) service availability and, 2) the handling of composer's beliefs. The latter refers to the fact that a service must not consider only two types of data to perform links, it should consider also the value of the instances, taking into account a same context. This work presents a new approach for the consumption of Linked Data in a service composition environment which uses as reference those links which have less probability of failing, selecting those services that can reduce the risk of a composition failure.