Relations Prediction for Knowledge Graph Completion using Large Language Models

Knowledge Graphs (KGs) are used to store semantic data in the form of entity nodes and edges. The edges represent the directed relations between the entities. For instance, the fact that James Cameron produced Avatar can be stored in a KG by having James Cameron node linked to Avatar node using the relation (edge) produced. This knowledge representation structure is called a triple; it consists of a head node, a relation, and a tail node. The direction in this triple is important to keep the validity of the fact if the nodes that surround the edge are swapped.