Report: ChatGPT & Perplexity Treat Structured Data As Text On A Page

To fuel the debate in the SEO world of the topic of structured data and LLMs and AI engines, we are hearing that once again, AI engines like ChatGPT and Perplexity are not using structured data in any special way.

Mark Williams-Cook ran another test, here is his previous test, and posted the results on LinkedIn. He basically created a fake company named DUCKYEA t-shirts.

On the page about DUCKYEA t-shirts, he did not post the fake company’s address. Instead, he put the address within made up JSON-LD schema markup. Then he waited and prompted both ChatGPT and Perplexity.

Both ChatGPT and Perplexity read the fake and made up schema to find the address. Since the schema was not valid, he figured that it was just being read by these AI engines like any other page of text on the web. “In my opinion, this test shows that the LLM agent is simply picking up whatever you are listing in the HTML. It does not matter if it is valid schema. If the system interprets the text as relevant to the prompt, it is included. It would therefore indicate that schema is *not* being used in the explicit sense it was designed for with those systems,” he wrote.

Here is the graphic from Mark:

To be fair, OpenAI did say it gets shopping results data from structured data feeds. John Mueller from Google said it depends when it comes to schema helping with LLMs. Microsoft explained how schema helps Copilot.

But as Mark Williams-Cook said, “The takeaway: Schema, good. Repackaging the basics as some magical new GEO formula, bad.”

Forum discussion at LinkedIn.