Recently, Large Language Models (LLM) have been used to generate structured graph data from unstructured text. However, parts of the extracted nodes lack information and retraining is necessary whenever the graph changes. We propose an unsupervised approach based on embeddings similarity, to link entities extracted by a LLM from unstructured text data to nodes of a knowledge graph, generated according to an ontology. Tested on three datasets from a maritime cyber security use case, results indicate an accuracy improvement from 86.2% up to 91,4%, depending on the number of neighbors and context candidate nodes.