# The Context Problem — Knowledge Graph Companion

**Article**: [The Context Problem: Token Economics and the Word That Means Everything](https://open.substack.com/pub/jessicatalisman/p/the-context-problem)
**Author**: [Jessica Talisman, MLS](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23jessicaTalisman)
**Publication**: [Intentional Arrangement](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23intentionalArrangement)
**Date**: March 11, 2026

**Companion RDF**: [Turtle](../rdf/the-context-problem-jessica-talisman-substack.ttl) · [JSON-LD](../rdf/the-context-problem-jessica-talisman-substack.jsonld)
**Interactive HTML**: [View Infographic](the-context-problem-jessica-talisman-substack.html)

---

## Overview

An analysis of how AI token economics has turned [context](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23context) into a billing unit, the grammatical sprawl of the word across noun/verb/adjective roles, and why [capacity is not coherence](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23capacityVsCoherence).

---

## Core Concepts

### [Context-as-Noun](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23contextAsNoun)

Context as the model's inputs and outputs — a long list where the AI model keeps a working memory for the conversation. The dominant usage in the industry.

### [Context-as-Verb](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23contextAsVerb)

The act of "contextualizing" — prepending background text to a prompt. Treats providing information as equivalent to establishing meaning.

### [Context-as-Adjective](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23contextAsAdjective)

Phrases like "contextual AI" and "context-aware systems" that claim relational intelligence while the underlying noun may only deliver statistical proximity.

### [Context Rot](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23contextRot)

Documented by [Chroma](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23chroma)'s 2025 study across 18 LLMs: as input length grows, model performance degrades even on simple tasks. Counterintuitively, shuffled context produced better retrieval than logically organized context.

### [Neurosymbolic AI](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23neurosymbolicAI)

The combination of data-driven and knowledge-driven techniques. [Knowledge graphs](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23knowledgeGraphs) and ontologies form the symbolic backbone; LLMs form the neural component. GraphRAG documented an 80% decrease in token usage vs. vector RAG.

### [Market for Lemons](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23marketForLemons)

Proposed by [George Akerlof](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23georgeAkerlof) (1970). Applied to AI: foundation companies define the token, control coherence mechanisms, and bear no disclosure obligation.

### [Credence Good](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23credenceGood)

Formalized by [Darby](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23michaelDarby) and [Karni](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23ediKarni) (1973). AI processing is a credence good — quality cannot be verified even after consumption.

---

## AI Model Pricing Comparison

| Model | Organization | Context Window | Input $/M | Output $/M | License |
|-------|-------------|----------------|-----------|------------|---------|
| [GPT-5.4 Pro](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gpt54Pro) | [OpenAI](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23openAI) | 1,050,000 | $5.00 | $180.00 | Proprietary |
| [Claude Opus 4.6](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23claudeOpus46) | [Anthropic](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23anthropic) | 1,000,000 | $5.00 | $25.00 | Proprietary |
| [Gemini 2.5 Flash](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gemini25Flash) | [Google](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23google) | 1,000,000 | $0.50 | $2.50 | Proprietary |
| [Grok 4.1 Fast](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23grok41Fast) | [xAI](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23xAI) | 2,000,000 | $0.20 | $0.50 | Proprietary |
| [Llama 4 Scout](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23llama4Scout) | [Meta](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23meta) | 10,000,000 | $0.08 | $0.30 | Open-weight |
| [Llama 4 Maverick](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23llama4Maverick) | [Meta](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23meta) | 1,000,000 | $0.15 | $0.60 | Community |
| [Grok 4](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23grok4) | [xAI](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23xAI) | 256,000 | $3.00 | $15.00 | Proprietary |

---

## FAQ

### [What is context in information science?](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23q1)

Context, in information science, describes the relational structure that holds meaning in place. It is not a container but the fabric that connects one element to another. From its Latin root *contextus* — the act of joining together (*con-* + *texere*, to weave) — context encodes a relational theory of meaning.

### [How has AI token economics changed the meaning of context?](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23q2)

AI token economics has turned context into a billing unit. Foundation AI companies leveraged the context craze, pushing the onus of poor AI performance back on users. The cost of using AI is associated with tokens, and tokens are directly attached to context.

### [What are the three grammatical roles of context in AI discourse?](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23q3)

Context-as-noun: the model's inputs and outputs, a working memory list. Context-as-verb: the act of prepending background text to a prompt. Context-as-adjective: phrases like "contextual AI" and "context-aware systems" that claim relational intelligence while the underlying noun may only deliver statistical proximity.

### [What is context rot?](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23q4)

Context rot is the phenomenon where model performance degrades as input length grows, even on deliberately simple and controlled tasks. Chroma's 2025 study evaluated 18 LLMs and documented that every model tested showed nonuniform performance degradation as tokens accumulated.

### [What is context engineering?](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23q5)

Context engineering is the art and science of curating what will go into the limited context window from that constantly evolving universe of possible information. The guiding principle is finding the smallest possible set of high-signal tokens that maximize the likelihood of some desired outcome.

### [How does the "Market for Lemons" apply to AI context pricing?](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23q6)

George Akerlof's 1970 theory describes markets where sellers know more about quality than buyers. In AI context pricing, foundation AI companies define the token, control the mechanisms that determine whether tokens cohere, and bear no disclosure obligation regarding coherence.

### [What is a credence good in the context of AI?](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23q7)

A credence good, formalized by Darby and Karni (1973), is a good whose quality cannot be verified even after consumption. AI token processing is a credence good: one can evaluate output quality after the fact, but cannot verify whether that output reflects coherent processing or stochastic inference.

### [How do knowledge graphs reduce token costs?](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23q8)

Passing a well-formed knowledge graph subgraph into a context window delivers more inferential signal per token than passing equivalent raw text. Research documented an 80% decrease in token usage when graph-based retrieval replaced conventional vector RAG methods.

### [Why is capacity not the same as coherence?](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23q9)

The market has priced capacity — how many tokens the model can see at once. What it has not priced is whether the relational structure within those tokens is coherent, navigable, or epistemically sound. Llama 4 Scout offers 10M tokens but effective context degrades at ~32,000 — a 300x gap.

### [What did Gartner recommend for AI value derivation?](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23q10)

Gartner identified three pillars: (1) A clear AI ambition tied to return on intelligence. (2) Trusted data systems and governance as the foundation for return on integrity. (3) People equipped with the skills to execute. Gartner also named composite and neurosymbolic AI as one of three future AI scenarios.

---

## Glossary

- **[Context](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt1)** — The relational structure that holds meaning in place. From Latin *contextus*: the act of joining together.
- **[Token](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt2)** — The smallest unit of information an AI model processes.
- **[Context Window](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt3)** — The amount of text, in tokens, that a model can consider at any one time.
- **[Context Rot](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt4)** — Performance degradation as input token length grows.
- **[Context Engineering](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt5)** — The art and science of curating the optimal set of tokens for the context window.
- **[Neurosymbolic AI](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt6)** — Combination of data-driven (neural) and knowledge-driven (symbolic) techniques.
- **[Knowledge Graph](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt7)** — A structured knowledge representation using explicit relationships.
- **[Market for Lemons](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt8)** — Akerlof's 1970 theory of markets with asymmetric information quality.
- **[Credence Good](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt9)** — A good whose quality cannot be verified even after consumption.
- **[Information Asymmetry](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt10)** — Sellers possess more information about product quality than buyers.
- **[Context-as-Noun](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt11)** — Context as the model's inputs and outputs.
- **[Context-as-Verb](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt12)** — The act of contextualizing — prepending background text.
- **[Context-as-Adjective](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt13)** — Phrases like "contextual AI" that claim relational intelligence.
- **[Byte Pair Encoding](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt14)** — A tokenization method that merges frequent character pairs.
- **[Compaction](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23gt15)** — Summarizes conversation history and reinitializes the context.

---

## How-To

### [1. Identify the grammatical role of context in your use case](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23step1)

Determine whether you need context-as-noun (working memory for conversation), context-as-verb (prepending background to prompts), or context-as-adjective (context-aware system design).

### [2. Apply context engineering techniques to manage token costs](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23step2)

Use compaction to summarize and reinitialize context. Implement structured note-taking to persist critical state outside the window. Deploy sub-agent architectures to isolate focused tasks.

### [3. Build neurosymbolic knowledge structures for coherence](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23step3)

Pass well-formed knowledge graph subgraphs into context windows. Use ontologies derived from relational databases to reduce overall LLM usage costs.

---

## SPARQL Queries

### [Describe the Article](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23article)

[Run live query](https://linkeddata.uriburner.com/sparql?default-graph-uri=&query=PREFIX%20schema%3A%20%3Chttp%3A%2F%2Fschema.org%2F%3E%0A%0ADESCRIBE%20%3Chttps%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23article%3E%0A%20%20%20%20%20%20%20%3Chttps%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%23jessicaTalisman%3E&format=text%2Fx-html-nice-turtle&timeout=0&debug=on&run=+Run+Query+)

```sparql
PREFIX schema: <http://schema.org/>

DESCRIBE <https://open.substack.com/pub/jessicatalisman/p/the-context-problem#article>
       <https://open.substack.com/pub/jessicatalisman/p/the-context-problem#jessicaTalisman>
```

### [Construct the FAQ Subgraph](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%2F%23sparql2)

[Run live query](https://linkeddata.uriburner.com/sparql?default-graph-uri=&query=PREFIX%20schema%3A%20%3Chttp%3A%2F%2Fschema.org%2F%3E%0A%0ACONSTRUCT%20%7B%0A%20%20%3Fq%20a%20schema%3AQuestion%20%3B%0A%20%20%20%20schema%3Aname%20%3Fname%20%3B%0A%20%20%20%20schema%3AacceptedAnswer%20%3Fa%20.%0A%20%20%3Fa%20a%20schema%3AAnswer%20%3B%0A%20%20%20%20schema%3Atext%20%3Ftext%20.%0A%7D%0AFROM%20%3Chttps%3A%2F%2Flinkeddata.uriburner.com%2FDAV%2Fdemos%2Fdaas%2Fthe-context-problem-jessica-talisman-substack.ttl%3E%0AWHERE%20%7B%0A%20%20%3Fq%20a%20schema%3AQuestion%20%3B%0A%20%20%20%20schema%3Aname%20%3Fname%20%3B%0A%20%20%20%20schema%3AacceptedAnswer%20%3Fa%20.%0A%20%20%3Fa%20schema%3Atext%20%3Ftext%20.%0A%7D&format=text%2Fx-html-nice-turtle&timeout=0&debug=on&run=+Run+Query+)

```sparql
PREFIX schema: <http://schema.org/>

CONSTRUCT {
  ?q a schema:Question ;
    schema:name ?name ;
    schema:acceptedAnswer ?a .
  ?a a schema:Answer ;
    schema:text ?text .
}
FROM <https://linkeddata.uriburner.com/DAV/demos/daas/the-context-problem-jessica-talisman-substack.ttl>
WHERE {
  ?q a schema:Question ;
    schema:name ?name ;
    schema:acceptedAnswer ?a .
  ?a schema:text ?text .
}
```

### [AI Models by Organization](https://linkeddata.uriburner.com/describe/?url=https%3A%2F%2Fopen.substack.com%2Fpub%2Fjessicatalisman%2Fp%2Fthe-context-problem%2F%23sparql3)

[Run live query](https://linkeddata.uriburner.com/sparql?default-graph-uri=&query=PREFIX%20schema%3A%20%3Chttp%3A%2F%2Fschema.org%2F%3E%0A%0ASELECT%20%3Fmodel%20%3FmodelName%20%3ForgName%20%3FcontextWindow%20%3FinputPrice%20%3FoutputPrice%0AWHERE%20%7B%0A%20%20GRAPH%20%3Chttps%3A%2F%2Flinkeddata.uriburner.com%2FDAV%2Fdemos%2Fdaas%2Fthe-context-problem-jessica-talisman-substack.ttl%3E%20%7B%0A%20%20%20%20%3Fmodel%20a%20schema%3ASoftwareApplication%20%3B%0A%20%20%20%20%20%20schema%3Aname%20%3FmodelName%20%3B%0A%20%20%20%20%20%20schema%3Amanufacturer%20%3Forg%20.%0A%20%20%20%20%3Forg%20schema%3Aname%20%3ForgName%20.%0A%20%20%20%20OPTIONAL%20%7B%20%3Fmodel%20%3AhasContextWindow%20%3FcontextWindow%20%7D%0A%20%20%20%20OPTIONAL%20%7B%20%3Fmodel%20%3AhasInputPricing%20%3FinputPrice%20%7D%0A%20%20%20%20OPTIONAL%20%7B%20%3Fmodel%20%3AhasOutputPricing%20%3FoutputPrice%20%7D%0A%20%20%7D%0A%7D%0AORDER%20BY%20%3ForgName%20%3FmodelName&format=text%2Fx-html%2Btr&timeout=0&debug=on&run=+Run+Query+)

```sparql
PREFIX schema: <http://schema.org/>

SELECT ?model ?modelName ?orgName ?contextWindow ?inputPrice ?outputPrice
WHERE {
  GRAPH <https://linkeddata.uriburner.com/DAV/demos/daas/the-context-problem-jessica-talisman-substack.ttl> {
    ?model a schema:SoftwareApplication ;
      schema:name ?modelName ;
      schema:manufacturer ?org .
    ?org schema:name ?orgName .
    OPTIONAL { ?model :hasContextWindow ?contextWindow }
    OPTIONAL { ?model :hasInputPricing ?inputPrice }
    OPTIONAL { ?model :hasOutputPricing ?outputPrice }
  }
}
ORDER BY ?orgName ?modelName
```

---

## Tools Used

- **[D3.js v7](https://d3js.org)** — Data-driven document manipulation for interactive graph visualization
- **[URIBurner](https://linkeddata.uriburner.com/fct)** — Linked Data resolver and SPARQL endpoint
- **[OpenLink Virtuoso](https://virtuoso.openlinksw.com)** — Universal server for RDF, SQL, and SPARQL
- **[kg-generator skill](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/kg-generator)** — Knowledge Graph generation
- **[rdf-infographic-skill](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/rdf-infographic-skill)** — Interactive HTML infographic generation
- **[RDF / SPARQL](https://www.w3.org/RDF/)** — W3C standards for knowledge representation and query

---

## Provenance

**Generated by**: [kg-generator skill](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/kg-generator) · [rdf-infographic-skill](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/rdf-infographic-skill)

**Generation environment**: [opencode](https://opencode.ai) · [qwen3.6-plus](https://www.alibabacloud.com/product/qwen)

**Entity links** use [URIBurner describe links](https://linkeddata.uriburner.com/fct) via the `{cname}/{describe}/{query}` pattern.