Tim Thompson
Manager, Metadata Services Unit, at Yale Library
Scalable Entity Resolution for Names in the Library Catalog
Tim Thompson
Manager, Metadata Services Unit
Yale Library
timothy.thompson@yale.edu
www.linkedin.com/in/timathompson
OCLC RLP AI Working Group: Subgroup 4
June 20, 2025
Attribution & Acknowledgments
- License
- Creative Commons Attribution 4.0 International (CC-BY).
- Credits
-
- Consultants:
- Gavin Mendel-Gleason
- Maren van Otterdijk
- Catherine Kwon (Yale, B.S. in Statistics & Data Science and Art)
- Anisia Hassan Ferreira Evangelista (Yale, B.A. in Economics, Statistics & Data Science, and Energy Studies)
- Yale Technical Services, Library IT, and Cultural Heritage IT (CHIT) Initiative
- Consultants:
For Yale’s new Cross Collection Discovery service to function effectively, the project requires a detailed entity reconciliation and disambiguation effort to determine variants of a term or name that refer to the same underlying concept, place or person.
– “Building Information Technology Collaboration Across Yale’s Museums and Libraries” (2019)
Authority Control
Who’s really in control here?
Authority Control in the Catalog
- Users depend on consistent access points to find what they’re looking for.
- Access points for people, groups, subjects (and to some extent works) are meant to be controlled and “authorized” against master files.
- In practice, authority control is messy because data is denormalized and entities are identified by strings rather than unique identifiers.
Catalog card taken from the digital version of the book Documentation made easy.
This Heading Is Valid?
Schubert, Franz
Will the Real Franz Schubert Please Stand Up?
- The lack of consistent, comprehensive authority control is a form of technical debt that impacts both users and library staff.
- Systems like Alma support integrated authority control processes, but we need to improve the quality of our data to use this functionality effectively.
Problem Statement
Entity Resolution
With some help from text embeddings?
1
2022–2023
Student employees (CHIT and library funded) used an Excel plugin to perform manual entity resolution and disambiguation for common names in the catalog.
3
November 2023
Pilot project proposal
5
September 2024–present
- Hired students
- Followed up with consultants on bug fixes and optimizations
- Carryied out further testing
- Developing Proof of Concept with Claude 3.7/4
2
2023
Research and testing with TerminusDB (open source graph database)
4
February–March 2024
Pilot project with consultants
Initial Steps
Training Data
- 2,539 names + records
- 81 identities
Key Concepts
Embeddings
Vector databases
HNSW, ANN...
Vector Databases
-
Embedding models transform text into a numeric representation.
-
Given a word or string of words, embedding models output a high-dimensional vector that captures the text’s semantic meaning, syntactic structure, and contextual nuance.
Credit: Catherine Kwon
[0.004, -0.005, ..., -0.017, 0.005]
“Today is a great day!”
string of text
high-dimensional vector
Text Embeddings
EMBEDDING
MODEL
Credit: Catherine Kwon
- Once you have a set of text embeddings, what do you do with them?
- Store them in a specialized index!
- Vector databases use indexing algorithms such as Hierarchical Navigable Small World (HNSW) graphs for Approximate Nearest Neighbor (ANN) search.
- As search engines, vector databases make it possible to return results based on user intent, rather than simple keyword matching.
Vector Databases
Embedding Strings
Contributor: Schubert, Franz
Title: The art of photography: instructions in the art of producing photographic pictures
Attribution: by G.C. Hermann Halleur ; with practical hints on the locale best suited for photographic operations, and on the proper posture, attitude, and dress, for portraiture by F. Schubert and an appendix ; translated from the German by G.L. Strauss
Subjects: Photography
Provision information: London: J. Weale, 1854
[0.007, -0.008, ..., -0.019, 0.001]
“Contributor: Schubert, Franz...”
high-dimensional vector
EMBEDDING
MODEL
Credit: Catherine Kwon
- Once embeddings are indexed, a vector database can calculate the “neighborhood” of each node based on a similarity threshold.
- The results can be converted to an edge list for graph visualization.
“Schubert, Franz”
- 88 records
- All 4 identities correctly clustered
- 4 unconnected nodes
- ~95% accuracy
- Threshold: 0.16
1
2
3
4
- Every person is different! Difficult to set a uniform threshold for similarity.
- Difficult to curate data and embedding strings.
- Trying to model a person’s identity (or identities) through their works is at best an approximation.
- Need a more nuanced approach.
Challenges and Limitations
Refining the Approach
Entity Resolution Pipeline with Logistic Regression
Why not just use an LLM?
Response from Claude Sonnet 4
LLM Cost Estimates
| Claude 3.5 Haiku | Claude 3.7 Sonnet | |
|---|---|---|
| Expected cost (1 input/output) |
$0.00029 |
$0.00403 |
| Name occurrences in the Yale catalog | 17,590,104 | 17,590,104 |
| Average comparisons per name | 18 | 18 |
| Total comparisons | 316,621,872 | 316,621,872 |
| Total | $91,820.34 | $1,275,986.14 |
Text Embedding Cost Estimates
| text-embedding-3-small | |
|---|---|
| Cost per 1M tokens | $0.02 |
| Name occurrences in the Yale catalog | 17,590,104 |
| Tokens per record | 200 |
| Total | $70.36 |
Why not just use an LLM to build a logistic regression pipeline?
Proof-of-Concept Entity Resolution Pipeline
by
Claude 3.7/4.0
Featuring Weaviate
Training a Classifier with Text Embeddings
See “Leveraging LLMs and Machine Learning for Record Matching,” blog post by Gavin Mendel-Gleason.
- Supervised machine learning method.
- Predicts a binary outcome.
- Outputs a probability.
Logistic Regression
Instead of just indexing a single embedding string, we need an entity resolution pipeline:
- preprocessing and deduplication
- embedding
- indexing
- imputation (vector “hot deck”)
- feature engineering (with interaction features)
- classification
- clustering
Logistic Regression Pipeline
- Vectorize individual fields.
- Choose a field as a key to filter and index based on similarity (e.g., person).
- Within each neighborhood, compare the entries and create a feature vector with the distance between vectors for each field.
- SetFit: few-shot fine-tuning of Sentence Transformers for classification using custom taxonomy.
Logistic Regression Pipeline
\vec{x}_0 = d(e1_{title}, e2_{title})
- Use gradient descent to train the model on labeled data.
- Output weights corresponding to each independent variable.
- Classify pairs of records as matching or not.
Logistic Regression Pipeline
Logistic Regression Pipeline
Domain Taxonomy
Graphic generated by Claude Opus 4
Results
| Performance Metrics | ||
|---|---|---|
| Metric | Value | |
| Precision | 0.9955 | |
| Recall | 0.8248 | |
| F1 | 0.9022 | |
| Accuracy | 0.8554 | |
| ROC AUC | 0.9917 | |
| Confusion Matrix | ||
| Predicted Negative | Predicted Positive | |
| Actual Negative | 2,816 | 45 |
| Actual Positive | 2,114 | 9,955 |
- Reproducible
- Interpretable
- Scalable
- Configurable
- Affordable
Classifier
LLM
- Black box
- Expensive
- Wasteful
- Smaller models are not as accurate.
Composite Vector Cosine Similarity
Person + Title Squared
[Photograph of Beinecke Construction]. 0AD. https://collections.library.yale.edu/catalog/2037090.
Work in Progress
Thank you!
Tim Thompson
1
2022–2023
Student employees (CHIT and library funded) used an Excel plugin to perform manual entity resolution and disambiguation for common names in the catalog
3
November 2023
Proposal to Marty Kurth and ITSC
5
September–October 2024
- Hiring students
- Following up with DataChemist on bug fixes and optimizations
- Carrying out further testing
2
2023
TerminusDB (graph database) and VectorLink: research and testing
4
February–March 2024
Consultant project with DataChemist (TerminusDB and VectorLink developers)
Consultant Project
Credit: Catherine Kwon
Dimensionality Reduction
Principal Component Analysis (PCA)
Ground Transportation
Credit: Catherine Kwon
Project Outcomes
Pipeline
- Export from Voyager
1
Extract
- Transform to BIBFRAME
- Generate embeddings strings
2
Transform
- Embed using OpenAI
- Index vectors in VectorLink
3
Load
Status
- Currently focused on people as contributors (vs. subjects).
- Testing with the curated benchmark dataset produced 2022–2023.
- 1,274 entries across 54 name/identity clusters.
Embedding Objects
{
"op": "Inserted",
"string": "Contributor: Schubert, Franz\n Title: The art of photography: instructions in the art of producing photographic pictures in any color, and on any material : for the use of beginners : and also of persons who have already attained some proficiency in the art : and of engravers on copper, stone, wood, etc.\n Subjects: Photography\n",
"marcKey": "7001 $aSchubert, Franz.",
"person": "Schubert, Franz",
"roles": "Contributor",
"title": "The art of photography: instructions in the art of producing photographic pictures in any color, and on any material : for the use of beginners : and also of persons who have already attained some proficiency in the art : and of engravers on copper, stone, wood, etc.",
"variant_titles": null,
"hub_title": null,
"subjects": "Photography",
"genres": null,
"record": "14703468",
"id": "14703468#Agent700-23"
}“Thayer, Nathaniel”
- 26 records
- 3 (4?) identities correctly clustered
- Some fragmentation of the main cluster
- Threshold: 0.16
1
2
3
4?
1a
1b
Redundant Data
Contributor: Halleur, G. C. Hermann
Title: The art of photography: instructions in the art of producing photographic pictures in any color, and on any material : for the use of beginners : and also of persons who have already attained some proficiency in the art : and of engravers on copper, stone, wood, etc.
Subjects: Photography
Contributor: Schubert, Franz
Title: The art of photography: instructions in the art of producing photographic pictures in any color, and on any material : for the use of beginners : and also of persons who have already attained some proficiency in the art : and of engravers on copper, stone, wood, etc.
Subjects: Photography
Library of Congress Names?
Name: Schubert, Franz, 1876-
Variant names: Schubert, Franz, b. 1876
Sources: Grundzüge der Pastoraltheologie, 1922 (Dr. Franz Schubert, o. ö. Professor an der Universität Breslau); DNB in VIAF, Oct. 7, 2011 (hdg.: Schubert, Franz, 1876-; German theologian, professor of pastoral theology); Deutsche Biographie, viewed 28 September 2022 (Franz Schubert; born in Bistrai-Bielitz (Austrian Silesia) in 1876, died in Breslau in 1937; Catholic theologian specializing in pastoral theology)
Contributor: Schubert, Franz
Title: Liturgische Zeitschrift
Subjects: Catholic Church--Liturgy--Periodicals.
Similarity: 0.23 😿
Bonus!
Simple RAG demo
Scalable Entity Resolution for Names in the Library Catalog
By Tim Thompson
Scalable Entity Resolution for Names in the Library Catalog
Discover innovative strategies for scalable entity resolution in library catalogs, exploring the power of text embeddings and vector databases. Join us to uncover solutions to enhance authority control and improve catalog accuracy!
