liveBook · Manning

Semantic type

As explained in Knowledge Graphs and LLMs in Action

A semantic type is a category that specifies the kind of entity represented by an ontology node, such as a disease, body structure, substance, or event.

A semantic type classifies an ontology entity by its domain category, such as body part, disease, sign or symptom, pharmaceutical product, or event. In biomedical integration, these categories make otherwise deep ontology nodes easier to identify and use. section 7.5.2 section 7.6.4

A graph-based semantic-type pipeline typically:

  • Loads ontology entities, relationships, names, and aliases into a graph. section 7.6.4
  • Uses hierarchical relationships such as SNOMED_IS_A to propagate categories from first-level nodes to deeper descendants. section 7.6.4 section 8.2
  • Connects entities across UMLS, SNOMED, and HPO so categorized medical concepts can support disambiguation and integration. section 7.5.2 section 7.6.4

UMLS classification

MRSTY.RRF categorizes Islets of Langerhans as “Body Part, Organ, or Organ Component,” Dengue fever as “Disease or Syndrome,” and Cephalgia as “Sign or Symptom.”

How Knowledge Graphs and LLMs in Action covers it

How deep it goes
Explains category storage and hierarchical propagation through SNOMED_IS_A, while stopping short of defining a universal taxonomy.
Examples
Uses UMLS MRSTY.RRF classifications and SNOMED hierarchy examples including diseases, body structures, substances, and events.
What it assumes
Assumes familiarity with ontology nodes and relationships, while showing how implicit SNOMED categories become explicit through propagation.
What you can do after
Build graph-based category propagation for medical entities using SNOMED relationships and Neo4j queries.
How it connects
Connects ontology, UMLS, SNOMED, HPO, named entity disambiguation, and knowledge-graph integration.
Cover of Knowledge Graphs and LLMs in Action
liveBookmanning.com
Read Knowledge Graphs and LLMs in Action on liveBook Get the book at manning.com

This explainer was generated by Manning's knowledge graph from the text of Knowledge Graphs and LLMs in Action. The section links point to the parts of the book it draws on.