Entity Grounding
stableCategory: entity · Methodology v4.5
Entity grounding measures how clearly your site declares its real-world identity to AI knowledge systems.
Signal Source
- Source
https://{domain}- Kind
- html_dom
Score Bands
| Verdict | Condition |
|---|---|
| Pass | Organization or Person JSON-LD schema is present with sameAs containing two or more authoritative targets (Wikipedia, Wikidata, or LinkedIn) |
| Partial | Organization or Person JSON-LD schema is present with exactly one authoritative sameAs target |
| Fail | no Organization or Person schema found, sameAs property absent, or all sameAs values point to non-authoritative targets |
Description
What this parameter measures
Entity grounding measures how clearly your site declares its real-world identity to AI knowledge systems. friendly4AI scans the homepage HTML for JSON-LD blocks with @type equal to Organization or Person, then reads the sameAs property — an array or string of external URLs that identify the same entity elsewhere on the web. Each sameAs value is tested against three authoritative entity-graph targets: wikipedia.org (any language edition), wikidata.org (Q-number URLs), and linkedin.com (company pages at linkedin.com/company/ or profile pages at linkedin.com/in/). The count of authoritative targets determines the tier. If no Organization or Person schema is present at all, the parameter scores zero regardless of any other structured data on the page.
Why it matters for AI-readiness
AI language models build entity knowledge by linking mentions to entries in knowledge graphs — primarily Wikidata and Wikipedia — and to social graph anchors like LinkedIn. When your Organization schema includes sameAs links to those sources, every AI system that processes your homepage can immediately resolve your entity, verify your identity, and increase confidence that citations about your organisation are accurate. Without sameAs grounding, the model must infer your entity from unstructured text alone, which introduces ambiguity, especially for organisations with common names. Strong entity grounding raises citation accuracy across ChatGPT, Gemini, Claude, Perplexity, and Bing Copilot — all of which query entity graphs when constructing factual answers.
How we score it
Under the v4.5 methodology, this Entity and Schema parameter scores on a three-tier gradient. It passes (100) when an Organization or Person JSON-LD block is present and sameAs contains at least two authoritative targets from Wikipedia, Wikidata, or LinkedIn. It scores partial (50) when the schema is present and sameAs contains exactly one authoritative target — grounding exists but is incomplete. It fails (0) when no Organization or Person schema is found, when sameAs is absent, or when all sameAs values point to non-authoritative targets (for example, only your own social media profiles or internal pages). The count is across all Organization and Person blocks on the page combined.
How to fix common issues
- Add a JSON-LD
Organizationblock to your homepage<head>(or inline as a<script type="application/ld+json">) with asameAsarray containing your Wikipedia article URL, your Wikidata entity URL (format:https://www.wikidata.org/wiki/Q<number>), and your LinkedIn company page URL. - If your organisation does not yet have a Wikipedia article, create a Wikidata entity first — Wikidata accepts entries for organisations without a Wikipedia article and issues a Q-number immediately.
- Ensure the
sameAsvalues are canonical: use the exact Wikipedia page URL (including language subdomain), thewikidata.org/wiki/Q…form, and thelinkedin.com/company/your-slugformat. - Reaching the pass tier requires two or more authoritative links; the minimum viable fix for partial → pass is adding a second authoritative target alongside whichever one you already have.
- Validate the full JSON-LD block with Google's Rich Results Test to confirm it parses without errors before re-scanning.
Version History
- Introduced
- v4.5
- Last changed
- v4.5
Key takeaways
- Signal: https://{domain}
- Category: Entity & Schema
- Passes when: Organization or Person JSON-LD schema is present with sameAs containing two o…