concept

ontology

Facts (40)

Sources

Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org arXiv 19 facts

referenceThe CSO Classifier is an ontology-driven system designed for the detection of research topics in scholarly articles, as described by Motta in the 2019 proceedings of the 23rd International Conference on Theory and Practice of Digital Libraries.

quoteEhrlinger et al. define a knowledge graph as a system that 'acquires and integrates information into an ontology and applies a reasoner to derive new knowledge.'

referenceThe Guider project uses the XI Pipeline to extract dependency graphs from logs for dependency-driven analytics, utilizing a manually developed ontology and tracking multi-level granular provenance over facts, events, and sources.

claimChanges to the underlying ontology or the configuration of the knowledge graph construction pipeline often require manual interaction or confirmation.

claimAssessing the quality of a Knowledge Graph is extremely challenging because there are many valid ways to structure and populate Knowledge Graphs, and even subproblems like evaluating the quality of a Knowledge Graph ontology are difficult.

claimA knowledge graph's ontology defines the concepts, relationships, and rules governing the semantic structure within a knowledge graph, including the types and properties of entities and their relationships.

claimValidating a knowledge graph's data integrity concerning its underlying semantic structure (ontology) is a specific quality aspect of knowledge graph construction.

procedureThe KARMA system provides a semi-automatic approach to link a structured source, such as a relational database, with an existing ontology. The process consists of four steps: (1) assigning semantic types to each column, (2) constructing a graph of all possible mappings between the source and the ontology, (3) refining the model based on user input, and (4) generating a formal specification of the source model.

claimThe World KG approach to knowledge graph construction manually verifies all matches to external ontologies for quality assurance.

referenceMethods for learning ontologies from relational databases focus on reverse engineering or using mappings to transform a relational database schema into an ontology or knowledge graph. Reverse engineering allows for the derivation of an Entity-Relationship diagram or conceptual model from the relational schema, though this requires careful handling of trigger and constraint definitions to prevent semantic loss.

procedureExtraction methods for semi-structured data typically combine data cleaning and rule-based mappings to transform input data into a knowledge graph, targeting defined classes and relations of an existing ontology.

procedureThe HKGB platform divides disease-specific information ingestion into two phases: building the Concept Knowledge Graph (ontology) and building the Instance Knowledge Graph.

claimDBpedia Live employs a freshness-oriented approach that continuously monitors ontology changes and immediately schedules affected entities for re-extraction.

claimKnowledge graphs use common ontology relationships such as 'is-a' and 'has-a' to represent taxonomic hierarchies and possessive relations between entities.

claimDBpedia requires manual changes to its ontology and data mappings, which must be loaded before running a new batch update.

procedureThe AutoKnow system performs taxonomy enrichment by extracting new types from input product catalogs and customer queries, then applying a Graph Neural Network (GNN) approach to place these new types into an existing ontology.

claimDBpedia enriches integrated knowledge graph data by attaching additional entity type information based on current ontology and relation data.

claimNELL and HKGB are knowledge graph systems that can identify new entity and relation types in input data for addition to the ontology after manual confirmation.

claimSemantic reasoning and inference allow for the validation of a knowledge graph's consistency based on a given ontology or individual structural constraints.

Enhancing LLMs with Knowledge Graphs: A Case Study - LinkedIn linkedin.com LinkedIn Nov 7, 2023 4 facts

referenceAn ontology models the knowledge of a specific domain, including entities and the relationships between them.

procedureThe authors linked coverage nodes in the ontology to the taxonomy services by generating a list of services and coverages using Cypher queries and programmatically creating relationships between them.

claimThe authors of the LinkedIn article 'Enhancing LLMs with Knowledge Graphs: A Case Study' utilized an ontology to structure data, binding it to taxonomy vertebrae to enable advanced reasoning, query, and recommendation capabilities.

procedureTo build the ontology, the authors identified entities and relationships from raw document text and used the GPT-4 Completion API to programmatically generate files in JSON Lines format for insertion into a graph database.

What are the challenges in maintaining a knowledge graph? - Milvus milvus.io Milvus 2 facts

claimMaintaining an accurate knowledge graph requires continuous updates and refinements to the ontology to accommodate new data and evolving real-world contexts, which is a time-consuming and resource-intensive process.

claimSemantic complexity presents a challenge in knowledge graph maintenance because the relationships between entities often involve multiple layers of meaning and context, requiring the development of a well-defined ontology.

KG-RAG: Bridging the Gap Between Knowledge and Creativity - arXiv arxiv.org arXiv May 20, 2024 2 facts

claimHeterogeneous Knowledge Graphs (KGs) include multiple types of nodes and relationships, guided by a defined ontology, whereas homogeneous Knowledge Graphs consist of only one type of node and relationship.

The construction and refined extraction techniques of knowledge ... nature.com Nature Feb 10, 2026 2 facts

procedureThe hybrid construction method for knowledge graphs integrates LLM-based extraction with ontology and rule constraints to support incremental updates and validation.

claimFuture development of the knowledge graph framework involves incorporating additional data types, such as document images, diagrams, tables, structured sources, and time-series logs, within the same ontology to quantify their incremental value against the text-only baseline.

The Mechanisms of Psychedelic Visionary Experiences - Frontiers frontiersin.org Frontiers Sep 27, 2017 1 fact

referenceDavid Luke's 2011 study, 'Disincarnate entities and dimethyltryptamine (DMT): psychopharmacology, phenomenology and ontology', explores the relationship between the hallucinogen DMT and the experience of encountering disincarnate entities.

A survey on augmenting knowledge graphs (KGs) with large ... link.springer.com Springer Nov 4, 2024 1 fact

claimA Knowledge Graph requires an ontology, which is a schema or structure that defines the types of entities, relationships, and associations within a domain context to provide semantic context and support reasoning and knowledge inference.

Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org Frontiers 1 fact

referenceKnowledge graphs are composed of entities (primary objects or concepts represented as nodes), relationships (connections between entities specifying interactions), attributes (properties or characteristics of entities), triples (facts represented as subject-predicate-object), and an ontology (the schema or structure organizing the graph).

Neurosymbolic AI: The Future of AI After LLMs - LinkedIn linkedin.com Charley Miller · LinkedIn Nov 11, 2025 1 fact

claimGraphMERT adheres to the strict rules of a professional-grade ontology, allowing it to provide breakthrough ideas from domain-specific data rather than the surface-level word correlations and hallucinations associated with GPT-based LLMs.

Addressing common challenges with knowledge graphs - SciBite scibite.com SciBite 1 fact

claimSciBite defines a knowledge graph as a semantic graph that integrates information into an ontology.

Combining Knowledge Graphs and Large Language Models - arXiv arxiv.org arXiv Jul 9, 2024 1 fact

referenceVamsi Krishna Kommineni, Birgitta König-Ries, and Sheeba Samuel developed an LLM-supported approach to ontology and knowledge graph construction, as described in their 2024 paper (arXiv:2403.08345).

LLM-empowered knowledge graph construction: A survey - arXiv arxiv.org arXiv Oct 23, 2025 1 fact

procedureThe knowledge extraction pipeline proposed by Kommineni et al. (2024) involves three steps: first, the Large Language Model generates Competency Questions (CQs) to define the knowledge scope; second, it constructs the corresponding ontology (TBox); third, it performs ABox population under explicit schema supervision, resulting in high consistency but limited flexibility.

Bridging the Gap Between LLMs and Evolving Medical Knowledge arxiv.org arXiv Jun 29, 2025 1 fact

referenceKG-Rank (Huang et al., 2021) and KG-RAG (Sanmartin, 2024) harness ontologies to re-rank evidence or enforce logical constraints, which improves factual consistency in long-form Question Answering (QA).

Knowledge Graphs: Opportunities and Challenges - Springer Nature link.springer.com Springer Apr 3, 2023 1 fact

claimThe schema for a knowledge graph is defined as an ontology, which describes the properties of a specific domain and how they are related, making ontology construction an essential stage of knowledge graph construction.

Applying Large Language Models in Knowledge Graph-based ... arxiv.org Benedikt Reitemeyer, Hans-Georg Fill · arXiv Jan 7, 2025 1 fact

referenceCarr et al. (2001) published 'Conceptual linking: ontology-based open hypermedia' in the Proceedings of the 10th international conference on World Wide Web, introducing ontology-based methods for hypermedia linking.

LLM Knowledge Graph: Merging AI with Structured Data - PuppyGraph puppygraph.com PuppyGraph Feb 19, 2026 1 fact

procedureThe GraphRAG pipeline operates in four steps: (1) Natural Language Processing and Hybrid Retrieval Strategy, where the system analyzes a user's natural language question to determine if a structured knowledge graph query is required; (2) Formal Query Code Generation, where the LLM reads the graph schema (ontology, entity types, and relationships) and generates the precise formal query code (e.g., Cypher or Gremlin) based on system prompts; (3) Query Execution and Result Return, where the knowledge graph engine performs structured traversal and multi-hop pathfinding to retrieve connected data points; and (4) Synthesis and Final Answer Generation, where the LLM uses the retrieved, verified, and structured results to formulate a coherent, context-rich, and grounded final answer.