cs.AIApr 3, 2026

OntoKG: Ontology-Oriented Knowledge Graph Construction with Intrinsic-Relational Routing

Authors: Yitao Li, Zhanlin Liu, Anuranjan Pandey, Muni Srikanth

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Organizing a large-scale knowledge graph into a typed property graph requires structural decisions -- which entities become nodes, which properties become edges, and what schema governs these choices. Existing approaches embed these decisions in pipeline code or extract relations ad hoc, producing schemas that are tightly coupled to their construction process and difficult to reuse for downstream ontology-level tasks. We present an ontology-oriented approach in which the schema is designed from the outset for ontology analysis, entity disambiguation, domain customization, and LLM-guided extraction -- not merely as a byproduct of graph building. The core mechanism is intrinsic-relational routing, which classifies every property as either intrinsic or relational and routes it to the corresponding schema module. This routing produces a declarative schema that is portable across storage backends and independently reusable. We instantiate the approach on the January 2026 Wikidata dump. A rule-based cleaning stage identifies a 34.6M-entity core set from the full dump, followed by iterative intrinsic-relational routing that assigns each property to one of 94 modules organized into 8 categories. With tool-augmented LLM support and human review, the schema reaches 93.3% category coverage and 98.0% module assignment among classified entities. Exporting this schema yields a property graph with 34.0M nodes and 61.2M edges across 38 relationship types. We validate the ontology-oriented claim through five applications that consume the schema independently of the construction pipeline: ontology structure analysis, benchmark annotation auditing, entity disambiguation, domain customization, and LLM-guided extraction.

Figures & tables

TypeModulePropertySample Values
 coreP571 inception1976-04-01
P856 official websitehttps://apple.com/
IntrinsiccorporationP1128 employees164,000; 154,000; 147,000; …
P1056 productsApple Watch, iPad, iPhone, …
RelationalaffiliationP112 founded bySteve Wozniak, Ronald Wayne, Steve Jobs
P127 owned byVanguard Group, Berkshire Hathaway, BlackRock
Table 1: Property organization for Apple Inc. (Q312), showing selected properties from a live Wikidata query (248 total). Core and intrinsic properties map to tabular output; relational properties become typed graph edges.
ScenarioCountInterpretation
All three agree4,840Consensus
AIDA wrong, Clean + Ours agree180AIDA error confirmed
Clean wrong, AIDA + Ours agree23CleanCoNLL error confirmed
All three disagree4Different error modes
Both NER differ from ontology84Linking errors or boundary cases
Unclassified (no gate match)298Cannot evaluate
Table 2: Three-way agreement on 5,429 shared entities (matched by Wikidata QID) between AIDA-YAGO and CleanCoNLL. The YAML classifier has no NER-specific tuning; a complete case-level breakdown of disagreement categories is provided in the project repository.
GroupCandidatesMentionsYAGOModule-Based (Our Approach)
1<5<510,28491.2%91.6%
25–91,66684.4%85.4%
310–1934882.5%82.8%
4≥20\geq 202568.0%76.0%
Macro Avg –81.5%83.9%
Table 3: Entity disambiguation accuracy on BLINK benchmark (12,323 controlled mentions with identical candidate lists). Module-based type annotations vs. YAGO 4.5 types, using Voyage rerank-2.5.
EntityCategoryTags
MercuryProductbrand, vehicle, transportation
Ford Motor CompanyOrganizationcorporation, transportation
Edsel FordPersoncreativity
Lincoln-Mercury DivisionOrganizationaffiliation, corporation
Table 4: LLM-guided entity extraction from a Wikipedia passage about Mercury (automobile), using the YAML schema as prompt instructions. Model: GPT-5-mini.
Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

FacetDomainOccupations
natural_scienceLife sciences, taxonomy, ecology22
humanitiesHistory, philosophy, languages, archaeology16
teachingPedagogy at all levels13
engineeringApplied sciences, computing11
physical_sciencePhysics, chemistry, earth sciences, math9
social_scienceEconomics, sociology, psychology6
Appendix
Table 5: Decomposition of the education module into 9 domain facets.
More in this topic

KG Construction

Knowledge graph construction turns text, tables, images, and databases into structured entities and relationships that machines can query and reason over.

See all 195 papers

Explore similar work

CardsList
Apr 3, 2026

Traceable Context-Enriched Knowledge Graph Generation with Induced Schemas

Knowledge graph generation typically relies either on predefined ontologies or on schema-free extraction. Ontology-driven pipelines enforce consistent typing but require costly schema design and maintenance, whereas schema-free methods often produce fragmented graphs with weak global organization, especially in long technical documents with dense, context-dependent information. We propose TRACE-KG (Text-dRiven schemA for Context-Enriched Knowledge Graphs), a framework that jointly constructs a context-enriched knowledge graph and an induced schema without assuming a predefined ontology. TRACE-KG captures conditional relations through structured qualifiers and organizes entities and relations using a data-driven schema that serves as a reusable semantic scaffold while preserving full traceability to the source evidence. Experiments show that TRACE-KG produces structurally coherent, traceable knowledge graphs and offers a practical alternative to both ontology-driven and schema-free construction pipelines. The code, experiments and prompts are available at https://github.com/mosadddeq01/TRACE-KG.

Mohammad Sadeq Abolhasani, Yang Ba, Yixuan He +1

School of Computing and Augmented Intelligence, Arizona State University, Tempe, USA · School of Mathematical and Natural Sciences, Arizona State University, Tempe, USA.

KG ConstructionKnowledge Representation
AskPDF
Sep 15, 2026

LLM-Guided Ontology-Driven Knowledge Graph Construction from Unstructured Text

Ontology-driven knowledge graph construction from industrial text remains challenging due to the domain specificity of documents, the scarcity of annotated resources, and the complexity of ontology engineering workflows. This paper presents and investigates the applicability of an ontology learning pipeline that combines compact open-source Large Language Models (LLMs), reusable prompting strategies, and open knowledge bases to support the extraction, structuring, enrichment, and evaluation of knowledge from textual corpora. The approach is tested and evaluated on a private French corpus of power-grid incident reports, using locally deployable open-source LLMs ranging from 7B to 32B parameters. Starting from unstructured reports, the approach extracts entities and relations, generates RDF triples, constructs related OWL ontology, enriches it using external knowledge sources, assesses the quality of the ontology, and subsequently constructs a populated knowledge graph grounded in the resulting ontology schema. Experiments on 80 manually annotated private reports show that schema-guided prompting significantly improves extraction quality, while quantized models provide an effective trade-off between performance and computational cost. These results demonstrate the feasibility of transforming domain-specific industrial text into ontology-based knowledge graphs using locally deployed open-source LLMs, while supporting the generalization of the extraction process through reusable prompting strategies.

Abdelhadi Belfadel, Maxence Gagnant, Joseph Kattan +1

Institute for Technological Research - IRT SystemX 2 Bd Thomas Gobert, 91120 Palaiseau, France.

KG ConstructionOntology LearningLLM Information Extraction
AskPDF
Jun 3, 2026

Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval

Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats, yet existing approaches either demand costly manual engineering or bypass structure entirely. We present a system that automatically discovers an executable schema from raw multi-source data and uses it as a shared contract for knowledge graph construction and query-time retrieval. A closed-world field catalog constrains LLM-based schema discovery to attested fields; deterministic structural analysis infers identity keys, foreign keys, and source hierarchy; and the resulting schema drives extraction, deduplication, and cross-source linking into a provenance-aware knowledge graph. At query time the schema -- optionally extended via a monotonic protocol -- conditions a multi-tool agent routing retrieval across structured lookup, graph traversal, and vector search, returning grounded answers with traceable citations. In controlled zero-shot comparisons using the same LLM, data, and evaluation harness, the system improves over retrieval-only and decomposition-based baselines across four QA benchmarks, with ablations showing that schema-conditioned routing, structural intelligence, and schema-guided construction each contribute to the gains.

Padmaja Jonnalagedda, Yuguang Yao, Xiang Gao +2

Intuit AI Research

KG ConstructionKnowledge RepresentationKnowledge Graph Question AnsweringHybrid RetrievalData Integration
AskPDF