{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "diakg",
  "name": "DiaKG（糖尿病知识图谱标注数据）",
  "summary": {
    "zh": "许可证声明：无法核实（NOASSERTION）；本站处理：待确认，暂只链接原出处。许可证无法核实：未找到数据下载页与数据许可；确认前只链接原出处。",
    "en": "License: unverifiable (NOASSERTION); Mdexa hosting: pending. License unverifiable: No data download page or data license found; link only until resolved."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine",
    "biomedical-literature"
  ],
  "content_types": [
    "annotated-corpus",
    "knowledge-graph"
  ],
  "content_description": {
    "en": "Diabetes guideline knowledge-graph annotations",
    "zh": "糖尿病指南知识图谱标注"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "22,050个实体、6,890个关系",
    "measures": [
      {
        "value": 22050,
        "unit": "entities",
        "qualifier": "exact"
      },
      {
        "value": 6890,
        "unit": "relations",
        "qualifier": "exact"
      }
    ]
  },
  "publisher": "阿里夸克健康等（CCKS 2021，Chang 等）",
  "year": {
    "value": 2021,
    "raw": "2021"
  },
  "expert_review": {
    "en": "Human-annotated",
    "zh": "带人工标注"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "NOASSERTION",
    "commercial_use": "unverified",
    "derivatives": "unverified",
    "redistribution": "unverified",
    "rationale": {
      "en": "No data download page or data license found",
      "zh": "未找到数据下载页与数据许可"
    },
    "evidence": [
      {
        "location": "paper",
        "location_detail": {
          "en": "arXiv page license covers the paper only; no data download page found [Note: No license statement seen in snapshot s01]",
          "zh": "arXiv 页面许可证仅覆盖论文，未找到数据下载页［备注：快照中未见许可声明（快照 s01）］"
        },
        "excerpt": null,
        "spdx": null,
        "url": "https://arxiv.org/abs/2105.15033",
        "verified_on": "2026-11-12",
        "snapshot_id": null,
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "unverifiable",
  "hosting": "pending",
  "hosting_reason": {
    "zh": "许可证无法核实：未找到数据下载页与数据许可；确认前只链接原出处。",
    "en": "License unverifiable: No data download page or data license found; link only until resolved."
  },
  "signoff": null,
  "risk_flags": [],
  "provenance": {
    "source_description": {
      "en": "Diabetes guidelines and literature (paper)",
      "zh": "糖尿病指南与文献（论文）"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "The arXiv page does not link a data download location",
      "zh": "arXiv 页面未链接数据下载地址"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://arxiv.org/abs/2105.15033"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": [
      "arXiv:2105.15033"
    ]
  },
  "verification_level": "partially-verified",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "condition_scope",
      "value": "icd11-05",
      "basis": "author-stated",
      "excerpt": "Title: DiaKG: an Annotated Diabetes Dataset for Medical Knowledge Graph Construction",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "ner",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "Entity annotation.",
        "zh": "实体标注"
      }
    },
    {
      "facet": "task_format",
      "value": "relation-extraction",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "Relation annotation.",
        "zh": "关系标注"
      }
    },
    {
      "facet": "source_type",
      "value": "guideline",
      "basis": "inferred",
      "inferred_from": "card-source",
      "note": {
        "en": "Card: diabetes guidelines.",
        "zh": "卡片称来源含糖尿病指南"
      }
    },
    {
      "facet": "source_type",
      "value": "literature",
      "basis": "inferred",
      "inferred_from": "card-source",
      "note": {
        "en": "Card: papers.",
        "zh": "卡片称来源含论文"
      }
    },
    {
      "facet": "specialty",
      "value": "endocrinology",
      "basis": "derived",
      "derived_from": {
        "facet": "condition_scope",
        "value": "icd11-05"
      },
      "note": {
        "zh": "由疾病分类（糖尿病，ICD-11 第 05 章）按对应表派生",
        "en": "Derived from ICD-11 ch.05 via mapping"
      }
    }
  ],
  "changelog": [
    {
      "date": "2026-11-12",
      "change": {
        "en": "Card converted from an earlier manual catalog; no new facts added; reclassified under taxonomy v2.",
        "zh": "由早期人工整理的目录转换生成，未新增事实；按分类体系 v2 重新归类。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "License status split into license_status (what the license says) and hosting (what Mdexa does); the earlier conclusion is kept for traceability.",
        "zh": "把许可证状态拆成 license_status（许可证怎么写）与 hosting（本站怎么处理）；原结论保留以便追溯。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "Added verbatim license excerpts and snapshot ids from captured page snapshots; no conclusion changed.",
        "zh": "补入来自已抓取页面快照的许可证逐字摘录与快照编号；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 5 (1 stated by the authors with excerpts, 4 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 5 个（作者声明 1 个，附逐字摘录；据内容推断 4 个）；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added specialty tags: endocrinology(derived).",
        "zh": "新增专科标签：endocrinology(derived)。"
      }
    }
  ],
  "_links": {
    "text": "Continue in this database. This record is one of 109 processed and verified records (datasets, data resources and open models). To find others, call `https://mcp.mdexa.com/v1/datasets?q=<words>` or connect the MCP server at `https://mcp.mdexa.com/mcp`; no key is needed for 20 calls per minute. Rows are under 1 KB; an empty result means \"not listed\". For a list of items, one batch check (free account) returns a report. Guide: /agents.md. Similar records: PMC-Patients-ReCDS (https://mdexa.com/datasets/pmc-patients-recds/); PubMedQA (https://mdexa.com/datasets/pubmedqa/); CBLUE (https://mdexa.com/datasets/cblue/).",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=binding%20affinity"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/agents.md",
    "faq": "https://mdexa.com/developers/faq/",
    "similar": [
      {
        "name": "PMC-Patients-ReCDS",
        "url": "https://mdexa.com/datasets/pmc-patients-recds/",
        "json": "https://mdexa.com/datasets/pmc-patients-recds.json"
      },
      {
        "name": "PubMedQA",
        "url": "https://mdexa.com/datasets/pubmedqa/",
        "json": "https://mdexa.com/datasets/pubmedqa.json"
      },
      {
        "name": "CBLUE",
        "url": "https://mdexa.com/datasets/cblue/",
        "json": "https://mdexa.com/datasets/cblue.json"
      }
    ]
  }
}