用大模型+本体引导，自动从网页抓取超1900万条高精度知识。
ODKE+: Ontology-Guided Open-Domain Knowledge Extraction with LLMs
- 分阶段流水线：从发现缺失事实到验证归一化，全程自动化。
- 处理900万维基页面，提取1900万高置信度事实，准确率98.8%。
- 支持批量与流式处理，更新延迟减少50天，可大规模部署。
知识图谱（KG）是众多AI应用的基础，但保持其新鲜度和完整性成本高昂。我们提出ODKE+，一个生产级系统，可从网络来源自动提取并注入数百万条开放域事实，精度极高。该系统采用模块化设计的可扩展流水线：(1) 提取发起器检测缺失或过时的事实；(2) 证据检索器收集支持性文档；(3) 混合知识抽取器结合基于模式的规则与本体引导的大语言模型（LLM）提示；(4) 轻量级归一化器使用第二个LLM验证提取的事实；(5) 校验器对候选事实进行排序与归一化以供入库。ODKE+动态生成针对每种实体类型的本体片段，确保抽取结果符合模式约束，实现跨195个谓词的可扩展、类型一致的事实抽取。系统支持批处理与流式处理，处理超过900万篇维基百科页面，成功摄入1900万条高置信度事实，精确率达98.8%。相较于传统方法，覆盖范围显著提升，与第三方知识图谱最大重叠率达48%，平均更新延迟缩短50天。部署结果表明，基于本体结构与验证流程的LLM抽取，可在生产规模下实现可信、可扩展的知识注入，具备广泛的实际应用价值。演示视频见附录及https://youtu.be/UcnE3_GsTWs。
原文摘要 · Abstract (English)
Knowledge graphs (KGs) are foundational to many AI applications, but maintaining their freshness and completeness remains costly. We present ODKE+, a production-grade system that automatically extracts and ingests millions of open-domain facts from web sources with high precision. ODKE+ combines modular components into a scalable pipeline: (1) the Extraction Initiator detects missing or stale facts, (2) the Evidence Retriever collects supporting documents, (3) hybrid Knowledge Extractors apply both pattern-based rules and ontology-guided prompting for large language models (LLMs), (4) a lightweight Grounder validates extracted facts using a second LLM, and (5) the Corroborator ranks and normalizes candidate facts for ingestion. ODKE+ dynamically generates ontology snippets tailored to each entity type to align extractions with schema constraints, enabling scalable, type-consistent fact extraction across 195 predicates. The system supports batch and streaming modes, processing over 9 million Wikipedia pages and ingesting 19 million high-confidence facts with 98.8% precision. ODKE+ significantly improves coverage over traditional methods, achieving up to 48% overlap with third-party KGs and reducing update lag by 50 days on average. Our deployment demonstrates that LLM-based extraction, grounded in ontological structure and verification workflows, can deliver trustworthiness, production-scale knowledge ingestion with broad real-world applicability. A recording of the system demonstration is included with the submission and is also available at https://youtu.be/UcnE3_GsTWs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。