An approach that provides hierarchical and index based watermarks represented as trees is described. In one embodiment, a watermark tree is formed from feature watermarks generated from a natural language processing (NLP) stack having NLP analytics. The watermark tree represents a hierarchical relationship between each of the feature watermarks. In particular, the watermark tree defines hierarchical pointers that point out inherited watermarks that exist between the feature watermarks according to the hierarchical relationship. Further, the watermark tree includes a time stamp specifying a time that a data set content residing in a corpus was accessed.