Unverified50% confidenceFactExact time
The team modeled provenance information as a graph structure: Document-PART_OF->Chunk<-MENTIONED_IN-Entity, and Entity-RELATES {rel_type, fact, spans}->Entity.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe character sheet prompt adopts a structured writing style, including sections such as subject_definitions, retention_analysis, and detailed_description.65% similarUnverifiedDocument-structure-based chunking uses the document's native organization as chunk boundaries, preserving the author's organizational intent and making each chunk a self-contained unit of knowledge.63% similarUnverified精准提示词模板分为三段式结构：功能描述、样式规范（具体到数值）、组件规范（指定构造器和参数）62% similarUnverifiedChoosing a chunking strategy should start from the types of information the document contains and the questions users will ask: use structure-aware splitting when headings are clear, recursive splitting when formatting is messy, consider semantic chunking when topic shifts are unmarked, use overlap to handle adjacent boundaries, use parent–child retrieval to recover surrounding explanations, and use late chunking to address context loss during embedding; these methods can be combined.62% similarUnverifiedBehind the form of Wikipedia is a set of content organization logic: entries can be broken down, entities reference each other, and definitions and details can be stored in layers.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063242API
curl https://kongchang.com/api/v1/knowledge/claims/1063242MCP
get_claim(id=1063242)