Unverified50% confidenceFactExact time
Query层的查询针对Ontology中的对象和关系，而非通过SQL直接操作底层表和字段，支持过滤、聚合、检查和沿关系链追溯
1
Sources
50%
Confidence
Long-term
Relevance
7/6/2026
First Seen
Sources
Deep Dive: How Palantir Agents Interact with the Ontology
bilibili零点未来7/4/2026
Related Claims
UnverifiedOntology查询接口设计与GraphQL思路高度相似，客户端精确声明所需字段和关系路径，避免over-fetching和under-fetching问题77% similarUnverifiedGraph databases store entities and relationships in the form of nodes and edges, and natively support multi-hop reasoning.72% similarUnverifiedTraditional Text-to-SQL solutions can only convert natural language into a single query, whereas Agent SQL can complete multi-turn interactions, including exploring table structures, generating queries, executing analyses, and automatically adjusting query logic.69% similarUnverified关系型数据库以表-行-列结构组织数据通过SQL查询，非关系型数据库以JSON文档等形式存储数据，牺牲一致性换取Schema灵活性68% similarUnverifiedSQLFluff、sqlcheck等SQL Linter通过解析SQL的抽象语法树（AST）来检测潜在问题67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/113963API
curl https://kongchang.com/api/v1/knowledge/claims/113963MCP
get_claim(id=113963)