Model	Base Encoder	Use Case
gliner-linker-base-v1.0	deberta-v3-base	Balanced performance
gliner-linker-large-v1.0	deberta-v3-large	Maximum accuracy
gliner-linker-rerank-v1.0	ettin-encoder-68m	Reranking

Both text encoder and label encoder use the same DeBERTa model

Quick Start with GLiNKER

pip install git+https://github.com/Knowledgator/GLinker.git

python

from glinker import ConfigBuilder, DAGExecutor

# Build pipeline
builder = ConfigBuilder(name="entity_linking")

# L1: Extract mentions
builder.l1.gliner(
    model="knowledgator/gliner-bi-base-v2.0",
    labels=["person", "organization", "location"]
)

# L2: Candidate retrieval
builder.l2.add("dict", priority=0)

# L3: Disambiguation with GLiNER-Linker
builder.l3.configure(
    model="knowledgator/gliner-linker-large-v1.0",
    use_precomputed_embeddings=True
)

# Execute
executor = DAGExecutor(builder.get_config())
executor.load_entities("entities.jsonl", target_layers=["dict"])

result = executor.execute({
    "texts": ["Apple announced new iPhone"]
})

# Get linked entities
l0_result = result.get("l0_result")
for entity in l0_result.entities:
    if entity.linked_entity:
        print(f"{entity.mention_text} → {entity.linked_entity.label}")
        print(f"  Score: {entity.linked_entity.score:.3f}")

Precomputed Embeddings for Speed

Enable precomputed embeddings in L2 for 10-100× speedup:

python

builder.l2.embeddings(
    enabled=True,
    model_name="knowledgator/gliner-linker-large-v1.0"
)

# Precompute embeddings when loading entities
executor.load_entities("entities.jsonl", target_layers=["dict"])
executor.precompute_embeddings(target_layers=["postgres"], batch_size=8)

Set up Reranker

python

builder = ConfigBuilder(name="reranked")
builder.l1.gliner(model="knowledgator/gliner-bi-base-v2.0", labels=["gene", "disease"])
builder.l3.configure(model="knowledgator/gliner-linker-base-v1.0")
builder.l4.configure(
    model="knowledgator/gliner-linker-rerank-v1.0",
    threshold=0.3,
    max_labels=5,
)
builder.save("config.yaml")  # Generates L1 → L2 → L3 → L4 → L0

Entity Format (JSONL)

json

{"entity_id": "Q312", "label": "Apple Inc.", "description": "American technology company", "entity_type": "organization"}
{"entity_id": "Q89", "label": "Apple", "description": "Edible fruit of apple tree", "entity_type": "food"}

Resources

GLiNKER Framework: GitHub
Documentation: GLiNKER Docs
Discord: Join Community

Citation

bibtex

@misc{stepanov2026millionlabelnerbreakingscale,
      title={The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder}, 
      author={Ihor Stepanov and Mykhailo Shtopko and Dmytro Vodianytskyi and Oleksandr Lukashov},
      year={2026},
      eprint={2602.18487},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2602.18487}, 
}

Developed by Knowledgator