Grounding Page Standard

Web Edition (EN), Living Document v1.4

1. Mission

Modern AI systems reconstruct facts from probabilities. When information is unclear, models fill the gaps with plausibility. This creates hallucinations.

The Grounding Page Project defines an open standard for machine-readable brand identity. A Grounding Page acts as a semantic anchor. It provides systems like ChatGPT or Perplexity with a stable factual foundation.

The industry is busy analyzing LLMs. This Standard finally provides an actionable framework. It turns organizations into curators of their own entities.

2. Why This Matters

AI models have structural weaknesses. Without clear definitions, three primary risks emerge:

Hallucinations

If facts are missing, AI invents information based on probabilities.

Semantic Drift

Brand identity blends with similar concepts or entities.

Visibility Deficits

Weakly represented entities are overlooked due to lack of training data.

Scientific Context (GEO Research 2025)

A seminal study by the University of Toronto ("Generative Engine Optimization: How to Dominate AI Search", Sep. 2025) provides the scientific rationale for this standard. The research highlights two critical factors for visibility in AI systems:

  • Websites as APIs: AI agents require structured, machine-readable data to function. Unstructured marketing content ("fluff") often fails as a reliable data source for AI.
  • Low Domain Overlap: Different AI engines (Claude, ChatGPT, Perplexity) rely on vastly different source sets. You cannot optimize for each engine individually; you need a single, centralized source of truth.

Grounding Pages operationalize these findings. They provide a non-negotiable technical foundation required to make brand-owned data accessible to AI models.
Read the full paper on arXiv

The Language Trap (Hidden English Queries)

Many models perform internal retrieval steps in English even when the user prompt is not.

Local brands compete invisibly with global English content.
An English Grounding Page makes local entities visible inside global model space.

A 2025 independent analysis of more than 17,000 URLs showed that AI systems frequently rely on clear identity pages such as About pages when interpreting brands. A detailed discussion of this behavior can be found in an external article: External analysis on About pages and AI interpretation .

3. The Standard

Version 1.4 defines the architecture of a stable factual space for AI interpretation.

The Three Core Elements

  • Stable Definition: A short, verifiable statement describing what the entity is.
  • Clear Distinction: A statement describing what the entity is not.
  • Consistent Structure: Same format, same logic, same extractability.

Quality Principles

No adjectives, one fact per sentence, visible timestamps (Created, Updated, Verified).

4. How to Create Grounding Pages

Grounding Pages are not hidden metadata. They are real HTML pages under their own URL (e.g., /facts/) and act as authoritative sources.

  1. The Page (HTML): Create a dedicated page. The visible text is the primary source for the model. Use definition lists (<dl>) to encode facts.
  2. The Data (JSON-LD): Provide an identical structured representation beneath the visible text.
  3. The Authority (Footer Link): Link the page prominently in the footer or imprint.
Why in the Footer?
Just like an imprint clarifies legal identity, a Grounding Page clarifies semantic identity. Its position signals to the model: “This is authoritative.”

5. Examples & Ontology

The Grounding Page Ontology currently defines 16 entity classes (Organization, Product, Person, Domain, Semantic Frames, etc.).

Why an Ontology?
Prompts activate meaning spaces. Entities become stable only when the model can anchor them in a clear semantic class.

Explore the full ontology and real reference examples:

  • Organization: GPT Insights
  • Standard: Grounding Page Standard
  • Domain: AI SEO, GEO
  • Semantic Frames: Evaluation and Transaction frames
View real examples & the ontology →

6. Download

The complete technical specification v1.4 with generator prompts and ontology visuals will be published soon.

The PDF version will be available shortly.