|
Persistent Identifier
|
doi:10.18419/DARUS-6299 |
|
Publication Date
|
2026-07-10 |
|
Title
| Replication Data for: AI-Assisted RDF Authoring from JSON Data |
|
Author
| Neubauer, Felixhttps://ror.org/04vnq7t77ORCIDhttps://orcid.org/0009-0008-5367-2034 |
|
Point of Contact
|
Use email button above to contact.
Neubauer, Felix (University of Stuttgart) |
|
Description
| This dataset accompanies the paper AI-Assisted RDF Authoring from JSON Data. It contains the metal-organic framework (MOF) synthesis JSON input used in the paper, the natural-language hints submitted to MetaConfigurator's AI assistant, the RML mappings generated from those hints, the RDF (JSON-LD) results obtained by executing the mappings, the SHACL shape used to validate the successful result, and the prompt, generated query, and CSV result of the AI-assisted SPARQL workflow.
The artifacts document three RML-generation runs and one SPARQL run: a minimal hint with gpt-4o (valid but shallow mapping), the same detailed hint with gpt-4o (retained as a failure case: unconditional parent-map links cause Cartesian products and drop required relations) and with gpt-5-mini (the successful case used in the paper), and a natural-language SPARQL request answered by gpt-5-mini. The prompts contain natural-language modeling instructions but no worked RML/Turtle snippets.
The deposited files are the exact artifacts evaluated in the paper. Model outputs can vary across invocations and service versions. See README.md for the full file inventory and reproduction instructions (including pySHACL validation). (2026-07-07) |
|
Subject
| Chemistry; Computer and Information Science |
|
Keyword
| Data Model http://www.wikidata.org/entity/Q1172480 (Wikidata)
JSON Schema http://www.wikidata.org/entity/Q24875054 (Wikidata)
Research Data Management http://www.wikidata.org/entity/Q30089794 (Wikidata)
Resource Description Framework http://www.wikidata.org/entity/Q54872 (Wikidata)
JSON-LD http://www.wikidata.org/entity/Q6108942 (Wikidata)
RDF Mapping Language http://www.wikidata.org/entity/Q108249512 (Wikidata)
SPARQL http://www.wikidata.org/entity/Q54871 (Wikidata)
SHACL http://www.wikidata.org/entity/Q29377821 (Wikidata)
Knowledge Graph http://www.wikidata.org/entity/Q33002955 (Wikidata)
Linked Data http://www.wikidata.org/entity/Q515701 (Wikidata)
Semantic Web http://www.wikidata.org/entity/Q54837 (Wikidata)
Ontology http://www.wikidata.org/entity/Q324254 (Wikidata)
Metal-Organic Framework http://www.wikidata.org/entity/Q909212 (Wikidata)
Large Language Model http://www.wikidata.org/entity/Q115305900 (Wikidata)
MetaConfigurator
Semantic Web http://id.loc.gov/authorities/subjects/sh2002000569 (LCSH)
RDF (Document markup language) http://id.loc.gov/authorities/subjects/sh2003010124 (LCSH)
MOFs http://id.loc.gov/authorities/subjects/sh2020006026 (LCSH) |
|
Topic Classification
| Computer Science (DFGFO) https://w3id.org/dfgfo/2024/443 |
|
Related Publication
| Is Supplement To: Neubauer, Felix, et al. (2026). MetaConfigurator: AI-Assisted RDF Authoring from JSON Data. arXiv Preprint. doi 10.48550/arXiv.2606.07094 https://doi.org/10.48550/arXiv.2606.07094
References: Neubauer, F., Endo, K., Bender, F., Ciftci, E., Hansen, N., Krause, S., Uekermann, B., Pleiss, J. (2026). Data Management and Analysis of Metal-Organic Framework Synthesis Using Data Models. Journal of Chemical Information and Modeling 66, 10, 5869-5879 doi 10.1021/acs.jcim.6c00542 https://doi.org/10.1021/acs.jcim.6c00542
References: Neubauer, F., Bredl, P., Xu, M., Patel, K., Pleiss, J., Uekermann, B. (2024). MetaConfigurator: A User-Friendly Tool for Editing Structured Data Files. Datenbank Spektrum 24, 161-169. doi 10.1007/s13222-024-00472-7 https://doi.org/10.1007/s13222-024-00472-7
References: Jafarkhani, Mahdi (2026). Connecting MetaConfigurator to the Semantic Web : RDF authoring, ontology integration, and knowledge graph support. Master thesis Univ. Stuttgart doi 10.18419/opus-18619 https://doi.org/10.18419/opus-18619 |
|
Notes
| The `rml:source` in the mappings is `Data.json` (the application's internal source name); rename `mof_synthesis_input.json` accordingly when running a mapping in another RML processor. LLM outputs are non-deterministic; the deposited mappings, RDF, query, and CSV are the exact artifacts from the paper. |
|
Producer
| Neubauer, Felix (University of Stuttgart)
Jafarkhani, Mahdi (University of Stuttgart) |
|
Funding Information
| DFG: 358283783 - SFB 1333
DFG: EXC 2075 - 390740016
DFG: NFDI4Chem: 441958208 |
|
Depositor
| Neubauer, Felix |
|
Deposit Date
| 2026-07-07 |