# Entity Linking

2 related articles

Subscribe to updates

arXiv Sep 28, 2026
CodeGraph annotates 145 million source files into a knowledge graph with about 1 billion typed edges and grounds its concepts in Wikidata
The work presents a pipeline that uses a code-specialised LLM (based on Qwen3-Coder-30B-A3B-Instruct) to annotate source files under an open taxonomy, extracting algorithms, paradigms, design patterns, and application domains, then grounds these in Wikidata through a three-stage procedure (deterministic SPARQL, a Deep Research Agent for the long tail, and parent-of hierarchy rollup), with a calibrated quality-assurance protocol combining a human gold set and an LLM-as-a-judge filter; applied to the Stack-Edu corpus it yields CodeGraph with roughly 158 million nodes (about 145 million file nodes, about 63,000 extracted concept entities, and roughly 19,800 grounded Wikidata entities) and about 1 billion typed edges across 14 programming languages.
The work presents a pipeline that uses a code-specialised LLM (based on Qwen3-Coder-30B-A3B-Instruct) to annotate source files under an open taxonomy, extracting algorithms, paradigms, design patterns, and application domains, then grounds these in Wikidata through a three-stage procedure (deterministic SPARQL, a Deep Research Agent for the long tail, and parent-of hierarchy rollup), with a calibrated quality-assurance protocol combining a human gold set and an LLM-as-a-judge filter; applied to the Stack-Edu corpus it yields CodeGraph with roughly 158 million nodes (about 145 million file nodes, about 63,000 extracted concept entities, and roughly 19,800 grounded Wikidata entities) and about 1 billion typed edges across 14 programming languages.
University of Bologna Scuola Superiore Sant'Anna
Federico Pennino（First author）
CodeGraph Knowledge Graph Construction Entity Linking LLM-as-a-Judge Source Code Mining
medRxiv Sep 13, 2026
Hybrid lexical-semantic retrieval over SNOMED CT: combining two retrieval paradigms to facilitate clinical data entry
The work proposes and implements a hybrid retrieval architecture that lets deterministic lexical matching and learned semantic matching coexist over SNOMED CT's own curated descriptions, combining multi-prefix search, BioLORD-2023-M embeddings, an optional BGE cross-encoder for re-ranking, and a local LLM for query normalization, with Reciprocal Rank Fusion and a hierarchy filter; on a search-only linking evaluation over 542 disease mentions from the DisTEMIST corpus (Spanish, zero-shot), semantic search with re-ranking and no LLM query pre-processing reached accuracy@1 of 0.60 and recall@10 of 0.80, and on 12,897 mentions from English real-EHR discharge notes a field-scoped typeahead placed the concept on the top-10 picker list for 73% of mentions (accuracy@1 0.
The work proposes and implements a hybrid retrieval architecture that lets deterministic lexical matching and learned semantic matching coexist over SNOMED CT's own curated descriptions, combining multi-prefix search, BioLORD-2023-M embeddings, an optional BGE cross-encoder for re-ranking, and a local LLM for query normalization, with Reciprocal Rank Fusion and a hierarchy filter; on a search-only linking evaluation over 542 disease mentions from the DisTEMIST corpus (Spanish, zero-shot), semantic search with re-ranking and no LLM query pre-processing reached accuracy@1 of 0.60 and recall@10 of 0.80, and on 12,897 mentions from English real-EHR discharge notes a field-scoped typeahead placed the concept on the top-10 picker list for 73% of mentions (accuracy@1 0.
Alejandro López Osornio（First author）
Hybrid concept retrieval SNOMED CT Reciprocal Rank Fusion Entity Linking

You’re all caught up

CodeGraph annotates 145 million source files into a knowledge graph with about 1 billion typed edges and grounds its concepts in Wikidata

Hybrid lexical-semantic retrieval over SNOMED CT: combining two retrieval paradigms to facilitate clinical data entry