demo-6-article-kg

The hardcore one: turn two live articles into a knowledge graph you can play with in the browser. You do all of it — you are the extractor (no NLP library) and you are the renderer (no graph library, no CDN, no framework). Two artifacts, one page that works the instant it lands.

Work the steps in order. Do not skip ahead to the HTML.

Step 0 — paths and plan

Both artifacts go in the output directory named in the Output default line at the very end of these instructions — normally .decode/outputs/, but a destination the human named always wins. Resolve it once, call it <OUT>, and use <OUT> everywhere below:

• <OUT>/graph.json — the extraction
• <OUT>/kg.html — the page

Put the pipeline in todo_write as five items (fetch, extract, render, verify, report) and write the real <OUT> path into the first one so you never re-derive it.

Step 1 — fetch the two sources

One web_fetch per URL (the tool returns Markdown):

• https://www.decodingai.com/p/understanding-neo4j-graph-agent-memory-system
• https://www.decodingai.com/p/ship-a-knowledge-graph-ontology-in-5-minutes

Keep the title and body prose. Ignore navigation, subscribe buttons, CTAs, comments, footers and trailing "read more" lists. If a fetch fails or comes back truncated, say so plainly and work with what you have — never invent content you did not fetch.

Step 2 — extract one merged graph

Distill ONE graph across both articles: an entity discussed in both articles is ONE node, not two. Write it to <OUT>/graph.json:

{
  "nodes": [
    {
      "id": "Ontology",
      "type": "concept",
      "desc": "one sentence in your own words"
    },
    { "id": "Neo4j", "type": "tool", "desc": "one sentence in your own words" }
  ],
  "edges": [{ "source": "Ontology", "target": "KG drift", "label": "prevents" }]
}

• 20–35 nodes. The key ideas, not every noun.
• type is exactly one of concept / tool / pattern / problem.
• desc is one sentence of your own synthesis, not a quote.
• Edges are directed; label is a short verb phrase (prevents, stores, queries).
• Every source and target matches a node id exactly — ids are case-sensitive.
• No orphans: every node has at least one edge.