EntityMap and AI Citations: Does an Entity Map Get You Cited by ChatGPT?
By Matt Cullerton, founder of Mavric and Apso
EntityMap is a proposed open standard for a JSON file that describes what a website knows, organized by entities like the business, its people and its products. A TikTok credits one for "over 13,000" citations from ChatGPT and Claude in a month. The dashboard showing that number is Microsoft's Bing AI Performance report, which counts Copilot and Bing citations, and nothing in the video shows the entity map caused the count.
The video comes from Robyn "Jam" Anderson (@jamout.ai) of Jam AI, a Denver AI marketing company. She demonstrates a builder tool inside her paid community that generates the file.
What is an EntityMap file?
entitymap.org describes it as "a proposed open standard for publishing a structured, entity-first index of website knowledge for AI systems." The site credits it as "Initiated by Fred Laurent with the support of Dixon Jones" and links it to Waikay and InLinks Optimization Ltd.
The v1.0 specification is dated April 7, 2026, marked Stable and licensed CC BY 4.0. It compares itself to sitemaps: "Where sitemap.xml tells crawlers what pages exist, entitymap.json tells AI systems what a site knows."
Two limits are worth knowing. The spec does not claim that any AI vendor or search engine reads the format. The site lists one implementation, the Waikay EntityMap Generator, and its certification registry "launches Q3 2026."
What do the 13,000 citations actually count?
The video opens with "ChatGPT and Claude have cited my website over 13,000 times this month." The screenshot behind that claim is headed "AI Performance," with the subhead "Citation sources: Microsoft Copilots and Partners," a 30-day range and a tile reading "Total Citations 13.2K."
That is the AI Performance report in Bing Webmaster Tools. Microsoft announced it on February 10, 2026, covering "Microsoft Copilot, AI-generated summaries in Bing, and select partner integrations." It counts citations "displayed as sources in AI-generated answers during the selected time frame." Microsoft does not name its partners, and neither ChatGPT nor Claude appears in the announcement.
OpenAI runs its own crawler for ChatGPT search. Its crawler documentation says "OAI-SearchBot is used to surface websites in search results in ChatGPT's search features."
Is an EntityMap file schema markup?
It is not. The video says the tool "creates that JSON schema markup file for you." In SEO, "schema markup" means schema.org vocabulary. Google's structured data intro says "Most Search structured data uses schema.org vocabulary," delivered as JSON-LD in a <script> tag on an HTML page.
The tool produces a different format. Its download buttons read "Download entitymap.json" and "Download entitymap.html," and it reports "passing every EntityMap v1.0 check."
The live file at jamout.ai/entitymap.json shows the difference. Its schema value is https://entitymap.org/spec/v1.0, and it holds 24 entities. It has no @context key. Its @type values include Organization, Person, Service and Event, which schema.org defines, and SoftwareProduct, Methodology, ProprietaryTerm and Concept, which return 404 on schema.org. Three more use a custom jam: prefix.
Using @type without @context makes the file look like JSON-LD at a glance. The JSON-LD 1.1 spec says a context "is used to map terms to IRIs." The file is served as application/json with no JSON-LD context link, so a JSON-LD processor has nothing to resolve its terms against. It is valid EntityMap, not schema.org markup.
Do you need special files to appear in AI answers?
Google says no, for its own AI features. Its AI features documentation says: "There are no additional requirements to appear in AI Overviews or AI Mode, nor other special optimizations necessary." And: "You don't need to create new machine readable files, AI text files, or markup to appear in these features. There's also no special schema.org structured data that you need to add."
That covers Google's AI Overviews and AI Mode, not Microsoft Copilot or other assistants. A clear HTML page describing a business is still a page that can be crawled and cited. The gap is between "a clear page about your business can be read and cited" and "this specific JSON file is why ChatGPT cites me."
Did the entity map cause the citations?
Nothing in the video shows that it did. She says the count is "because I have a super good entity map." The file's generated timestamp is October 23, 2026 at 17:27 UTC. The video posted about twenty hours later. The dashboard shows a 30-day range, so almost all the counted citations came before the current entity map existed.
The dashboard also reports "Avg. Cited Pages 17," meaning citations spread across many pages on the site. The site also publishes an llms.txt file, so there are at least two machine-readable files plus ordinary pages. The video shows no before-and-after comparison.
How does the Entity Map Builder work?
In the video, the tool takes a website URL, reads a few pages and lists the entities it found. The demo runs on friendassembly.com, a Denver ceramics studio, and reports "I read 6 pages" and "14 things you're known for." Users check the entities, confirm "I checked these and they're accurate," download the files and follow instructions for one of ten platforms, from WordPress to Vercel and Netlify.
Bottom line
EntityMap is a real, documented proposed standard, but no AI vendor has said it reads the format. The 13,000-citation figure comes from Microsoft's Bing AI Performance report, which covers Copilot, Bing and unnamed partners, not ChatGPT or Claude by name. The file is not schema.org markup, and Google says no special files are needed for its AI features. The video does not show the entity map caused the citations.
Sources
- EntityMap overview, entitymap.org - the standard and its authors
- EntityMap v1.0 specification - version, status and registry date
- Introducing AI Performance in Bing Webmaster Tools - what the citation report covers
- AI features and your website, Google Search Central - no special files required
- Intro to structured data, Google Search Central - schema.org and JSON-LD
- Getting started with schema.org - the schema.org vocabulary
- JSON-LD 1.1, W3C - contexts and terms
- Overview of OpenAI Crawlers - OAI-SearchBot and ChatGPT search
- Jam AI EntityMap, jamout.ai - the rendered entity map
- entitymap.json, jamout.ai - the live file
- llms.txt, jamout.ai - the site's llms.txt
Published October 24, 2026. Based on a TikTok by @jamout.ai. Full video notes (markdown)