DROPS

Artifact

Software

MYAMR_TGDK

Authors: Wilma Johanna Schmidt, Irlan Grangel-González, Adrian Paschke, and Evgeny Kharlamov

Abstract

Cite as

Wilma Johanna Schmidt, Irlan Grangel-González, Adrian Paschke, Evgeny Kharlamov. MYAMR_TGDK (Software, Source code, example data set). Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@misc{dagstuhl-artifact-25262,
   title = {{MYAMR\underlineTGDK}}, 
   author = {Schmidt, Wilma Johanna and Grangel-Gonz\'{a}lez, Irlan and Paschke, Adrian and Kharlamov, Evgeny},
   note = {Software, partially funded by https://graph-massivizer.eu/, partially funded by https://www.smarty-project.eu/, partially funded by https://enrichmydata.eu/ (visited on 2025-12-10)},
   url = {https://github.com/boschresearch/myamr_tgdk},
   doi = {10.4230/artifacts.25262},
}

Document

Use Case

DOI: 10.4230/TGDK.3.3.5

LLM-Supported Manufacturing Mapping Generation

Authors: Wilma Johanna Schmidt, Irlan Grangel-González, Adrian Paschke, and Evgeny Kharlamov

Published in: TGDK, Volume 3, Issue 3 (2025). Transactions on Graph Data and Knowledge, Volume 3, Issue 3

Abstract

In large manufacturing companies, such as Bosch, that operate thousands of production lines with each comprising up to dozens of production machines and other equipment, even simple inventory questions such as of location and quantities of a particular equipment type require non-trivial solutions. Addressing these questions requires to integrate multiple heterogeneous data sets which is time consuming and error prone and demands domain as well as knowledge experts. Knowledge graphs (KGs) are practical for consolidating inventory data by bringing it into the same format and linking inventory items. However, the KG creation and maintenance itself pose challenges as mappings are needed to connect data sets and ontologies. In this work, we address these challenges by exploring LLM-supported and context-enhanced generation of both YARRRML and RML mappings. Facing large ontologies in the manufacturing domain and token limitations in LLM prompts, we further evaluate ontology reduction methods in our approach. We evaluate our approach both quantitatively against reference mappings created manually by experts and, for YARRRML, also qualitatively with expert feedback. This work extends the exploration of the challenges with LLM-supported and context-enhanced mapping generation YARRRML [Schmidt et al., 2025] by comprehensive analyses on RML mappings and an ontology reduction evaluation. We further publish the source code of this work. Our work provides a valuable support when creating manufacturing mappings and supports data and schema updates.

Cite as

Wilma Johanna Schmidt, Irlan Grangel-González, Adrian Paschke, and Evgeny Kharlamov. LLM-Supported Manufacturing Mapping Generation. In Transactions on Graph Data and Knowledge (TGDK), Volume 3, Issue 3, pp. 5:1-5:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@Article{schmidt_et_al:TGDK.3.3.5,
  author =	{Schmidt, Wilma Johanna and Grangel-Gonz\'{a}lez, Irlan and Paschke, Adrian and Kharlamov, Evgeny},
  title =	{{LLM-Supported Manufacturing Mapping Generation}},
  journal =	{Transactions on Graph Data and Knowledge},
  pages =	{5:1--5:22},
  ISSN =	{2942-7517},
  year =	{2025},
  volume =	{3},
  number =	{3},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/TGDK.3.3.5},
  URN =		{urn:nbn:de:0030-drops-252164},
  doi =		{10.4230/TGDK.3.3.5},
  annote =	{Keywords: Mapping Generation, Knowledge Graph Construction, Ontology Reduction, RML, YARRRML, LLM, Manufacturing}
}

Document

DOI: 10.4230/LIPIcs.ICDT.2020.10

On Equivalence and Cores for Incomplete Databases in Open and Closed Worlds

Authors: Henrik Forssell, Evgeny Kharlamov, and Evgenij Thorstensen

Published in: LIPIcs, Volume 155, 23rd International Conference on Database Theory (ICDT 2020)

Abstract

Data exchange heavily relies on the notion of incomplete database instances. Several semantics for such instances have been proposed and include open (OWA), closed (CWA), and open-closed (OCWA) world. For all these semantics important questions are: whether one incomplete instance semantically implies another; when two are semantically equivalent; and whether a smaller or smallest semantically equivalent instance exists. For OWA and CWA these questions are fully answered. For several variants of OCWA, however, they remain open. In this work we adress these questions for Closed Powerset semantics and the OCWA semantics of [Leonid Libkin and Cristina Sirangelo, 2011]. We define a new OCWA semantics, called OCWA*, in terms of homomorphic covers that subsumes both semantics, and characterize semantic implication and equivalence in terms of such covers. This characterization yields a guess-and-check algorithm to decide equivalence, and shows that the problem is NP-complete. For the minimization problem we show that for several common notions of minimality there is in general no unique minimal equivalent instance for Closed Powerset semantics, and consequently not for the more expressive OCWA* either. However, for Closed Powerset semantics we show that one can find, for any incomplete database, a unique finite set of its subinstances which are subinstances (up to renaming of nulls) of all instances semantically equivalent to the original incomplete one. We study properties of this set, and extend the analysis to OCWA*.

Cite as

Henrik Forssell, Evgeny Kharlamov, and Evgenij Thorstensen. On Equivalence and Cores for Incomplete Databases in Open and Closed Worlds. In 23rd International Conference on Database Theory (ICDT 2020). Leibniz International Proceedings in Informatics (LIPIcs), Volume 155, pp. 10:1-10:21, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2020)

Copy BibTex To Clipboard

@InProceedings{forssell_et_al:LIPIcs.ICDT.2020.10,
  author =	{Forssell, Henrik and Kharlamov, Evgeny and Thorstensen, Evgenij},
  title =	{{On Equivalence and Cores for Incomplete Databases in Open and Closed Worlds}},
  booktitle =	{23rd International Conference on Database Theory (ICDT 2020)},
  pages =	{10:1--10:21},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-139-9},
  ISSN =	{1868-8969},
  year =	{2020},
  volume =	{155},
  editor =	{Lutz, Carsten and Jung, Jean Christoph},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ICDT.2020.10},
  URN =		{urn:nbn:de:0030-drops-119343},
  doi =		{10.4230/LIPIcs.ICDT.2020.10},
  annote =	{Keywords: Incomplete Databases, Cores, Semantics, Open and Closed Worlds}
}

Search Results

Documents authored by Kharlamov, Evgeny

MYAMR_TGDK

Abstract

Cite as

LLM-Supported Manufacturing Mapping Generation

Abstract

Cite as

On Equivalence and Cores for Incomplete Databases in Open and Closed Worlds

Abstract

Cite as

Thanks for your feedback!

Could not send message