"SIFT will develop Plan Recognition for Multi-Source Reasoning Over Sources and Events (PRIMROSE) to provide high-performance, probabilistic plan recognition to DTRA, addressing the intelligence analysis problem of information overload. PRIMROSE will perform high-performance plan recognition and integrate the results into JIPOE-based intelligence processes. In PRIMROSE: (1) the YAPPR2 plan recognition component will parse disparate feeds of event descriptions to extract likely adversary and neutral party plans and goals; (2) the role extractor (ROLEX) will identify key agents in relevant plans and assemble network analysis diagrams; and (3) SIFTs SPIRE graph modeling system will evaluate the resulting networks and COAs. PRIMROSE will develop new techniques for temporal reasoning, provenance management, and entity extraction for plan recognition."