Our structured data named a founder, and the fix was to name nobody

Five sites, five separate repositories, one hand-copied TypeScript file. That file is the only reason a crawler can tell the five domains come from one company rather than being five unrelated sites that link to each other. It has been rewritten three times in three days, and every rewrite was driven by the same rule: the structured data is not allowed to say anything the page does not say. The first shape was the obvious one. A PUBLISHER constant with a name and an @id, a list of the apps, and every site emitting the same publisher identifier.