# Hidden relationships in a document-derived property graph: top-k chunk embeddings and inverse-distance weighting over a dynamically evolving ontology

arXiv: https://arxiv.org/abs/2609.00387 · HTML: https://mlsanity.com/paper/2609.00387/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Matryoshka Representation Learning](https://mlsanity.com/paper/2205.13147/) (2022)
- [Foundations of Modern Query Languages for Graph Databases](https://mlsanity.com/paper/1610.06264/) (2016)
- [Graph Pattern Matching in GQL and SQL/PGQ](https://mlsanity.com/paper/2112.06217/) (2021)
- [RedisGraph GraphBLAS Enabled Graph Database](https://mlsanity.com/paper/1905.01294/) (2019)
- [A fixed storage distributed graph database hybrid with at-scale OLAP expression and I/O support of a relational DB: Kinetica-Graph](https://mlsanity.com/paper/2201.02136/) (2022)
- [Novel data structures for label based queries specifically efficient for billion+ property graph networks using Kinetica-Graph](https://mlsanity.com/paper/2311.03631/) (2023)
- [An Ad-hoc graph node vector embedding algorithm for general knowledge graphs using Kinetica-Graph](https://mlsanity.com/paper/2407.15906/) (2024)

## Abstract (arXiv)

Large language models extracting knowledge graphs from text capture only explicitly stated facts, often leaving semantically related entities disconnected across documents. We present an additive, engine-neutral second pass that discovers these latent ties without altering extracted facts. Each document is chunked and embedded once; top-k nearest- neighbor queries across existing chunks yield candidate node pairs via entity membership maps. Candidate pairs are scored using Shepard inverse-distance weighting with a rescaled chord distance metric, avoiding the threshold-collapsing flaw of affine cosine scoring behind a k-NN gate. Un-gated per-pair accumulators form a commutative monoid, ensuring the pipeline is strictly order-independent and scales incrementally without recomputing prior documents. Implemented across FalkorDB, Kinetica, ArangoDB, and Neo4j, our method shows that 768- and 240-dimensional embeddings retain 92% and 72% edge fidelity against a 3072-D baseline while achieving a 25x faster top-k formulation.