Applying Transfer-Learning based on pre-trained language models has become popular in Natural Language Processing. In this paper, we present a weakly supervised Named Entity Recognition system that uses a pre-trained BERT model and applies two consecutive fine tuning steps. We aim to reduce the amount of human labour required for annotating data by proposing a framework which starts by creating a data set that uses lexicons and pattern recognition on documents. This first noisy data set is used in the first fine tuning step. Then, we apply a second fine tuning step on a small manually refined subset of data. We apply and compare our system with the standard fine tuning BERT approach on large amount of old scanned document. Those documents are North Sea Oil & Gas reports and the knowledge extraction would be used to assess the possibility of future carbon sequestration. Furthermore, we empirically demonstrate the flexibility of our framework showing that it can be applied to entity-identifications in other domains.