This paper describes the process of automatic extraction of implicit--global--data from explicit information by file inversion and threading. Each datum is the symbolic representation of a proposition, and as such has a number of movable parts corresponding to the ideal elements of the proposition represented; e.g., subject, predicate. A third element is expressed by word order--the relationship between subject and predicate. Appropriate relationships are: is included in; includes; intersects; and excludes. The predicate is the "classifier" of the subject. Inversion consists of turning data around, putting the subject in the place of the predicate and some permutation of the predicate in place of the subject, while changing the sense of the relation--normally from "is included in" to "includes." In this way the series of data with the same subject, instead of describing a single entity, becomes the inventory of a broad class, bringing together things with common attributes. Threading forms a data organization where the subject of each datum after the first is identical with the term in the predicate of at least one of the preceding data. This can become a powerful research tool. (Author/MBR)