Skip to Content

Knowledge Graph Generator

Context

A Knowledge Graph is a structured representation of information that captures the relationships between entities such as concepts, people, and organizations. In this representation, Nodes represent entities and Arcs represent the semantic relationships between them.

The relationship types include seven families:

Taxonomic

Expresses an “is-a” link. For example, a kidney stone is a calculus. It encodes class membership and hierarchy.

Partitive

Expresses a “part-of” link. For example, a nephron is part of a kidney. It captures meronymy and composition.

Attributive

Expresses a “has-property” link. For example, urine has the property acidity. It associates entities with their characteristics.

Causal

Expresses a “causes” or “influences” link. It is a directed dependency in which one entity influences another.

Functional

Expresses a “used-for” or “enables” link. For example, an NSAID is used-for pain relief. It captures purpose and capability.

Temporal

Expresses an “occurs-before” or “results-in” link. It encodes ordering and sequence in time.

Spatial

Expresses a “located-in” or “next-to” link. For example, a calculus is located-in the ureter. It captures geometric and topological placement.

Function Overview

The Knowledge Graph Generator is a Hellixia feature that builds a complete Knowledge Graph from scratch using Large Language Models. It extracts both the nodes (entities) and the semantic relationships between them entirely from the knowledge encoded in LLMs, without requiring you to supply any nodes beforehand.

Available Knowledge Graph Generators

Menus > Hellixia > Semantic Knowledge Graph Generator, which requires a node as a starting point, with an optional knowledge file.

Menus > Hellixia > Document Analysis > Knowledge Graph Generator, which builds the graph using a Knowledge File as the central element, grounding the output in a supplied document rather than purely in the LLM’s internal knowledge.

Examples