# Entity Disambiguation on Wikidata-Disamb 30 (test)

Source: [Entity Disambiguation on Wikidata-Disamb 30 (test)](<https://www.sota2.com/research/sota/entity-disambiguation-on-wikidata-disamb-30-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:58:16.272Z

Evaluation of Entity Disambiguation performance on the test split of the Wikidata-Disamb 30 dataset, measured using Precision, Recall, and F1 scores.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Entity Disambiguation |
| Dataset (including any stated split) | Wikidata-Disamb 30 (test) |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Precision](<https://www.sota2.com/research/sota/entity-disambiguation-on-wikidata-disamb-30-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/entity-disambiguation-on-wikidata-disamb-30-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/entity-disambiguation-on-wikidata-disamb-30-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| XLNet + 1&2-hop KG Context | 91.93 | Not recorded | 68fa68491e209131cea1b161 |
| XLNet + 1-hop KG Context | 91.55 | Not recorded | 68fa68491e209131cea1b161 |
| RoBERTa + 1-hop KG Context | 91.48 | Not recorded | 68fa68491e209131cea1b161 |
| LSTM+RNN-triplets+ATN | 90.2 | Not recorded | 68fa68491e209131cea1b161 |
| LSTM + RNN-triplets | 90.1 | Not recorded | 68fa68491e209131cea1b161 |
| RoBERTa + 1&2-hop KG Context | 89.88 | Not recorded | 68fa68491e209131cea1b161 |
| XLNet-without KG context | 89.32 | Not recorded | 68fa68491e209131cea1b161 |
| RoBERTa - without KG context | 89.09 | Not recorded | 68fa68491e209131cea1b161 |

### XLNet + 1&2-hop KG Context

Precision: 91.93. Result ID: 698d66b38b517eb4332139e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

[Implementation](<https://github.com/mulangonando/Impact-of-KG-Context-on-ED>)

Recorded evaluation configuration: {"Backbone":"XLNet","KG context":"1&2-hop"}. This record does not assert independent reproduction.

### XLNet + 1-hop KG Context

Precision: 91.55. Result ID: 698d66b38b517eb4332139df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

[Implementation](<https://github.com/mulangonando/Impact-of-KG-Context-on-ED>)

Recorded evaluation configuration: {"Backbone":"XLNet","KG context":"1-hop"}. This record does not assert independent reproduction.

### RoBERTa + 1-hop KG Context

Precision: 91.48. Result ID: 698d66b38b517eb4332139dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

[Implementation](<https://github.com/mulangonando/Impact-of-KG-Context-on-ED>)

Recorded evaluation configuration: {"Backbone":"RoBERTa","KG context":"1-hop"}. This record does not assert independent reproduction.

### LSTM+RNN-triplets+ATN

Precision: 90.2. Result ID: 698d66b38b517eb4332139da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

Recorded evaluation configuration: {"Context":"triplets","Attention":true}. This record does not assert independent reproduction.

### LSTM + RNN-triplets

Precision: 90.1. Result ID: 698d66b38b517eb4332139d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

Recorded evaluation configuration: {"Context":"triplets"}. This record does not assert independent reproduction.

### RoBERTa + 1&2-hop KG Context

Precision: 89.88. Result ID: 698d66b38b517eb4332139de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

[Implementation](<https://github.com/mulangonando/Impact-of-KG-Context-on-ED>)

Recorded evaluation configuration: {"Backbone":"RoBERTa","KG context":"1&2-hop"}. This record does not assert independent reproduction.

### XLNet-without KG context

Precision: 89.32. Result ID: 698d66b38b517eb4332139dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e61e209131cea1300d.md>)

[Implementation](<https://github.com/zihangdai/xlnet>)

Recorded evaluation configuration: {"Backbone":"XLNet","KG context":"None"}. This record does not assert independent reproduction.

### RoBERTa - without KG context

Precision: 89.09. Result ID: 698d66b38b517eb4332139db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68491e209131cea1b161.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Backbone":"RoBERTa","KG context":"None"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.