In 2023, researchers found success in using large language models (LLMs) in the task of entity alignment. [41] This was in particular thanks to their effectiveness at producing syntactically meaningful embeddings.[42]

Entity alignment methods use these structural similarities between generally non-isomorphic graphs to predict which nodes correspond to the same entit

the same entity will inevitably be represented in multiple graphs. However, because no single standard for the construction or representation of knowledge graph exists, resolving which entities from disparate graphs correspond to the same real world subject is a non-trivial task. This task is known as knowledge graph entity alignment, and is an active area of research.[38]

A knowledge graph formally represents semantics by describing entities and their relationships.[31] Knowledge graphs may make use of ontologies as a schema layer. By doing this, they allow logical inference for retrieving implicit knowledge rather than only allowing queries requesting explicit knowledge.[32]

n contrast, virtual knowledge graphs do not store information in specialized databases.[29] They rely on an underlying relational database or data lake to answer queries on the graph. Such a virtual knowledge graph system must be properly configured in order to answer the queries correctly. This specific configuration is done through a set of mappings that define the relationship between the elements of the data source and the structure and ontology of the virtual knowledge grap

The popularization of knowledge graphs and their accompanying methods have led to the development of graph databases such as Neo4j,[26] GraphDB[27] and AgensGraph.[28] These graph databases allow users to easily store data as entities and their interrelationships, and facilitate operations such as data reasoning, node embedding, and ontology development on knowledge bases.

The development of large language models expanded interest in knowledge graphs as a way to structure information from unstructured text, with advances in language processing enabling their automatic or semi-automatic generation and expansion.[15][16][17] The term knowledge graph has since broadened to include the dynamically constructed and adaptive graph structures, which support retrieval, reasoning, and summarization in generative systems. Microsoft Research's GraphRAG (2024) exemplified this development by integrating LLM-generated graphs into retrieval-augmented generation.

2. A Schema-RAG system using a Knowledge Graph operates differently:The AI first consults the ontology to understand the question’s components.It finds that Support Ticket is a class linked via a property referencesProduct to the Product class.It discovers that the Product class has a property called productType, and that ‘Connected Service’ is a specific instance of that type.Armed with this understanding of the relationships, it constructs a precise, formal query (SPARQL) to retrieve only the tickets that conform to this logic.

Knowledge Graphs provide the semantic context, constraints and explicit relationships that LLMs lack. This enables true reasoning, like navigating a map of your business, instead of just text retrieval.

Standard Retrieval-Augmented Generation (RAG) over documents is a good first step, but it fails when faced with complex, cross-domain enterprise questions. It finds text that looks similar, which isn’t the same as finding facts that are related.