{"id":6851,"date":"2026-02-09T12:34:20","date_gmt":"2026-02-09T12:34:20","guid":{"rendered":"https:\/\/www.stanventures.com\/news\/?p=6851"},"modified":"2026-02-09T12:34:20","modified_gmt":"2026-02-09T12:34:20","slug":"ai-models-show-limited-distinction-for-schema-markup","status":"publish","type":"post","link":"https:\/\/www.stanventures.com\/news\/ai-models-show-limited-distinction-for-schema-markup-6851\/","title":{"rendered":"AI Models Show Limited Distinction for Schema Markup"},"content":{"rendered":"

AI systems, including ChatGPT and Perplexity, appear to treat structured data embedded in webpages as ordinary text rather than as a distinct machine-readable signal, according to a new test shared by an SEO researcher, adding to uncertainty about how such models interpret schema markup.<\/b><\/p>\n

A recent experiment suggests that large language models may not interpret <\/span>structured data<\/span><\/a> in the way publishers and search professionals expect.<\/span><\/p>\n

Mark Williams-Cook, an SEO consultant, said he tested how ChatGPT and Perplexity handle schema markup by creating a fictional clothing brand, DUCKYEA T-shirts, and publishing a webpage for it. The page did not display the company\u2019s address in visible content. Instead, the address was placed only inside JSON-LD schema markup.<\/span><\/p>\n

\"<\/p>\n

The schema markup was intentionally invalid.<\/span><\/p>\n

When both AI systems were asked about the company\u2019s address, they returned the fabricated information contained in the schema, despite its lack of validity. Williams-Cook said the results suggest the models read schema as part of the page\u2019s text rather than processing it as structured data with defined rules.<\/span><\/p>\n