Making Inconsistency Respectable: Part 2 - Meta-level handling of inconsistency

Inconsistency in a database, when viewed purely logically, seem undesirable. Indeed the traditional approach to dealing with inconsistency in data is to employ means to restore consistency immediately. However, it is important to study the larger environment containing such databases, and the circumstances surrounding the inconsistency. We argue that within the larger environment, an inconsistency can be desirable, and useful, if we know appropriate actions to handle it. In some cases we may wish to remove the inconsistency , and in other cases we may wish to keep it. Moreover, we claim that inconsistencies only become meaningful when considered in the context of the larger environment, and in particular, of how they arise and are handled. In this paper we present a meta-level system that uses actions for handling inconsistent databases.