SiGNaL³
Wolfgang Fahl
This page in other languages: de
⚠️ LLM-generated content notice: Parts of this page may have been created or edited with the assistance of a large language model (LLM). The prompts that have been used might be on the page itself, the discussion page or in straight forward cases the prompt was just "Write a mediawiki page on X" with X being the page name. While the content has been reviewed it might still not be accurate or error-free.
Acronym[edit]
SiGNaL³ - Simple Strategic Superior Graph Navigation Language
Superior Visualization Through LLMs[edit]
When visiting the node Earth of the knowledge graph, an appropriate visualization of the node and relevant possible paths/edges should be visualized. With the power of state-of-the-art Large Language Models, the selection of the visualization should be feasible in a way that is superior to traditional knowledge graph exploring approaches.
The Earthrise Symbol[edit]
The Earthrise (Q843864) picture is a symbol for the relation between Moon, Earth and Human (Q5). When mankind was capable of taking this viewpoint it was a groundbreaking moment in human history and the picture is iconic in the semiotic sense.
The file "mwstore://local-backend/local-public/diagrams/archive/20251018082134!Diagrams_a0d07af584998e15983ad0aa04cfff5a.png" already exists.
Content[edit]
[edit]
Triples of two nodes linked by a relation are the core elements of knowledge graphs (KGs). Navigating such a graph in a human friendly / natural / simple way is mandatory for successful usage of such knowledge graphs.
Strategic Subgraph Availability[edit]
The strategic move now is to make sure relevant subgraphs are readily available to fulfill needs of projects based on the use cases and use case scenarios of a project.
Such scenarios fortunately can be described with sets of situation/action/expected result descriptions:
- A situation describes a relevant subgraph in a concrete state
- The action describes what a system should be offering as an API working on the situation subgraph
- The expected result is describing the result subgraph potentially with modifications that have been applied
Natural Language to Graph Traversal[edit]
Natural language use case descriptions may be transformed to augmented knowledge graph traversals this way. The journey through the knowledge graph may be interactive.
Knowledge Graph Exploration Application[edit]
A first application is knowledge graph exploration. The traversal path and the human input gathered on the way may now be used to:
- Create a relevant subgraph
- Generate an abstract description of the subgraph that allows stakeholders to create a local copy
- Enable project stakeholders to work with the local copy by modifying and extending
- Provide synchronization of this local KG with the original KG (respecting privacy settings)
SiGNaL³ Tour Example: Earth to Human Consciousness[edit]
Starting from Earth (Q2):
The file "mwstore://local-backend/local-public/diagrams/archive/20251018082134!Diagrams_8639870807e74744343e299ad969e9aa.png" already exists.
Interactive Journey Elements[edit]
- Situation: User at Earth node, interested in human space exploration
- Action: SiGNaL³ RAG system identifies Moon→Apollo→Earthrise pathway as most meaningful
- Expected Result: User gains understanding of how space exploration changed human consciousness
Advantages Over Traditional Approaches[edit]
| Traditional KG Navigation | SiGNaL³ RAG-Enhanced Navigation |
|---|---|
| Manual node clicking | Intelligent pathway suggestions |
| All edges shown equally | Contextually relevant edges prioritized |
| Static visualizations | Dynamic, story-driven presentations |
| Technical interface | Human-friendly natural language interaction |
| No narrative context | Rich semiotic and historical context |
Use Case Scenarios[edit]
Research Discovery[edit]
- Situation: Researcher exploring climate change impacts
- Action: Start from Earth (Q2), RAG identifies pathways through atmosphere, greenhouse gases, temperature records
- Result: Curated subgraph of climate-related concepts with temporal relationships
Educational Tours[edit]
- Situation: Student learning about space exploration
- Action: Interactive tour from Earth→Moon→Mars with historical context
- Result: Engaging narrative connecting astronomical facts to human achievement
Technical Foundation[edit]
SiGNaL³ leverages:
- Wikidata as primary knowledge graph source
- SPARQL for semantic queries and relationship extraction
- Large Language Models for context understanding and path optimization
- Graphviz for human-readable relationship visualization
Links[edit]
- SiGNaL - Original Simple Graph Navigation Language
- Earth on Wikidata
- Moon on Wikidata
- Earthrise on Wikidata
- Human on Wikidata