I personally and professionally used these to do some cool things, like run audits across different systems simultaneously. Common stack would include Protege for creating the ontologies (i.e., a schema of how the things you're interested in link to each other), Ontotext Refine or py scripts to populate the graphs, and Ontotext GraphDB or Neo4j AuraDB for storing them.
It's relatively easy to then connect this knowledge base to an LLM, and get more flexibility out of it.
That said, there aren't that many user-friendly tools that get the most out of KGs. Most people I worked with weren't interested in KGs or knowledge bases themselves, they just wanted their particular problem solved. And often, it was easier to justify purchasing a subscription to managed tools that (claim to) solve the problem.
So, unless you're OK with building some middleware to combine user apps with KGs, it won't stick with others, in my experience.