PIPE-RDF: 一个基于LLM的企业RDF基准测试流水线
PIPE-RDF: An LLM-Assisted Pipeline for Enterprise RDF Benchmarking
AI总结：
PIPE-RDF通过反向查询和检索增强提示构建企业RDF基准测试，生成450个问题-SPARQL对，实现100%有效性验证。
摘要：
企业依赖RDF知识图谱和SPARQL通过自然语言接口暴露操作数据，但公开的KGQA基准测试不反映专有模式、前缀或查询分布。我们提出了PIPE-RDF，一个三阶段流水线，通过反向查询、类别平衡的模板生成、检索增强提示、去重和基于执行的验证与修复，构建特定模式的NL-SPARQL基准测试。我们在一个固定模式的公司位置切片（5000家公司）上实例化PIPE-RDF，该切片来自公开的RDF数据，生成了覆盖九个类别的450个问题-SPARQL对的平衡基准。流水线在修复后实现了100%的解析和执行有效性，修复前的有效率在各阶段为96.5%-100%。我们报告了实体多样性指标、模板覆盖率分析和成本分解，以支持部署规划。我们发布了结构化艺术制品（CSV/JSONL、日志、图表）和操作指标，以支持模型评估和系统规划的实际应用。代码可在https://github.com/suraj-ranganath/PIPE-RDF上获得。
英文摘要：
Enterprises rely on RDF knowledge graphs and SPARQL to expose operational data through natural language interfaces, yet public KGQA benchmarks do not reflect proprietary schemas, prefixes, or query distributions. We present PIPE-RDF, a three-phase pipeline that constructs schema-specific NL-SPARQL benchmarks using reverse querying, category-balanced template generation, retrieval-augmented prompting, deduplication, and execution-based validation with repair. We instantiate PIPE-RDF on a fixed-schema company-location slice (5,000 companies) derived from public RDF data and generate a balanced benchmark of 450 question-SPARQL pairs across nine categories. The pipeline achieves 100% parse and execution validity after repair, with pre-repair validity rates of 96.5%-100% across phases. We report entity diversity metrics, template coverage analysis, and cost breakdowns to support deployment planning. We release structured artifacts (CSV/JSONL, logs, figures) and operational metrics to support model evaluation and system planning in real-world settings. Code is available at https://github.com/suraj-ranganath/PIPE-RDF.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
