And I'm wondering as LLMs have been brought into the set of capabilities, how that's changing some of the landscape or at least the expectations of the ability to do entity extraction and resolution.

Yeah, we get asked that a lot recently.

It's a sort of question investors will ask is, well, can LLMs do everything that you're doing? And there's this wonderful German word, which is Jein, which is a portmanteau of Ja und Nein together, which means kinda.

And that's the answer because...

You know, if you put in a thousand records into any large language model and say, ask it, you know, which of these records belong together, then you're going to get a reasonably good output.

The problem, as you said, comes from the difference between running a nice demo, which, you know, works on your desktop with a small volume of data and actually doing something which is reliable in production and at scale.

So we do believe that large language models do have a a place in entity resolution, but it's not in production.

And one of the challenges that I often see when talking to people about graph databases or graph structural representations is in terms of how how much they want to invest in the graph for purposes of things like graph based machine learning or being able to do long and complex node traversals because of the fact that you end up with super nodes, which complicates your ability to be able to shard across multiple machines, which then causes you to have to Yeah, so.