Most of the previous works in the field of extraction pattern are based on the usage of syntactic analyzer and semantic tagger to create a pattern that could extract relevant information from free text documents or more structured documents like web pages. In this paper, we propose an approach to create a set of extraction pattern by combining a particular Part Of Speech (POS) tagger and Grammatical Parser, i.e. Stanford POS Tagger and Link Grammar Parser (LG). The extraction pattern will be used in a Name Entity Recognition (NER) system to identify the occurrences of some entities in free text documents. We demonstrate the algorithm on accident report as a case study. © 2009 IEEE.