# Entity Disambiguation on Entity Disambiguation Suite (Zero-shot, BLINK Candidates)

Source: [Entity Disambiguation on Entity Disambiguation Suite (Zero-shot, BLINK Candidates)](<https://www.sota2.com/research/sota/entity-disambiguation-on-entity-disambiguation-suite-zero-shot-blink-candidates>)

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

Data updated: 2026-02-26T05:22:27.294Z

Evaluation of Zero-shot Entity Disambiguation performance across the combined suite (AIDA, MSNBC, AQUAINT, ACE2004, CWEB, WIKI) using candidates generated by the BLINK model on the test split.

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) | Entity Disambiguation Suite Zero-shot (AIDA, MSNBC, AQUAINT, ACE2004, CWEB, WIKI) BLINK Candidates (test) |
| Metric | AIDA Score |
| 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

- [AIDA Score](<https://www.sota2.com/research/sota/entity-disambiguation-on-entity-disambiguation-suite-zero-shot-blink-candidates.md?metric=AIDA%20Score>): Higher is better; unit: PERCENT.

- [MSNBC Score](<https://www.sota2.com/research/sota/entity-disambiguation-on-entity-disambiguation-suite-zero-shot-blink-candidates.md?metric=MSNBC%20Score>): Higher is better; unit: PERCENT.

- [AQUAINT Score](<https://www.sota2.com/research/sota/entity-disambiguation-on-entity-disambiguation-suite-zero-shot-blink-candidates.md?metric=AQUAINT%20Score>): Higher is better; unit: PERCENT.

- [ACE2004 Score](<https://www.sota2.com/research/sota/entity-disambiguation-on-entity-disambiguation-suite-zero-shot-blink-candidates.md?metric=ACE2004%20Score>): Higher is better; unit: PERCENT.

- [CWEB Score](<https://www.sota2.com/research/sota/entity-disambiguation-on-entity-disambiguation-suite-zero-shot-blink-candidates.md?metric=CWEB%20Score>): Higher is better; unit: PERCENT.

- [WIKI Score](<https://www.sota2.com/research/sota/entity-disambiguation-on-entity-disambiguation-suite-zero-shot-blink-candidates.md?metric=WIKI%20Score>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/entity-disambiguation-on-entity-disambiguation-suite-zero-shot-blink-candidates.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AIDA Score | Result date | Report paper |
| --- | --- | --- | --- |
| BART-large+KILM\_DU | 82.1 | Not recorded | 68fa6e991e209131cea40fe0 |
| BART-large+KILM | 80.1 | Not recorded | 68fa6e991e209131cea40fe0 |
| BLINK | 79.6 | Not recorded | 68fa6e991e209131cea40fe0 |
| BART-large+KILM\_End | 79.6 | Not recorded | 68fa6e991e209131cea40fe0 |
| BART-base+KILM | 75.1 | Not recorded | 68fa6e991e209131cea40fe0 |
| BART-base+Merge | 19.5 | Not recorded | 68fa6e991e209131cea40fe0 |
| BART-base | 18.3 | Not recorded | 68fa6e991e209131cea40fe0 |
| BART-large | 17.4 | Not recorded | 68fa6e991e209131cea40fe0 |

### BART-large+KILM\_DU

AIDA Score: 82.1. Result ID: 699049543a6c314849ff7877.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Implementation](<https://github.com/alexa/kilm>)

Recorded evaluation configuration: {"#Params":"406M","Protocol":"Zero-shot","Candidates":"BLINK"}. This record does not assert independent reproduction.

### BART-large+KILM

AIDA Score: 80.1. Result ID: 699049543a6c314849ff7876.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Implementation](<https://github.com/alexa/kilm>)

Recorded evaluation configuration: {"#Params":"406M","Protocol":"Zero-shot","Candidates":"BLINK"}. This record does not assert independent reproduction.

### BLINK

AIDA Score: 79.6. Result ID: 699049543a6c314849ff7871.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68641e209131cea1bbab.md>)

Recorded evaluation configuration: {"#Params":"336M","Protocol":"Zero-shot","Candidates":"BLINK"}. This record does not assert independent reproduction.

### BART-large+KILM\_End

AIDA Score: 79.6. Result ID: 699049543a6c314849ff7878.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Implementation](<https://github.com/alexa/kilm>)

Recorded evaluation configuration: {"#Params":"406M","Protocol":"Zero-shot","Candidates":"BLINK","Ablation variant":"KILM\_End"}. This record does not assert independent reproduction.

### BART-base+KILM

AIDA Score: 75.1. Result ID: 699049543a6c314849ff7874.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Implementation](<https://github.com/alexa/kilm>)

Recorded evaluation configuration: {"#Params":"139M","Protocol":"Zero-shot","Candidates":"BLINK"}. This record does not assert independent reproduction.

### BART-base+Merge

AIDA Score: 19.5. Result ID: 699049543a6c314849ff7873.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

Recorded evaluation configuration: {"#Params":"139M","Protocol":"Zero-shot","Candidates":"BLINK"}. This record does not assert independent reproduction.

### BART-base

AIDA Score: 18.3. Result ID: 699049543a6c314849ff7872.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66921e209131cea10fff.md>)

Recorded evaluation configuration: {"#Params":"139M","Protocol":"Zero-shot","Candidates":"BLINK"}. This record does not assert independent reproduction.

### BART-large

AIDA Score: 17.4. Result ID: 699049543a6c314849ff7875.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40fe0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66921e209131cea10fff.md>)

Recorded evaluation configuration: {"#Params":"406M","Protocol":"Zero-shot","Candidates":"BLINK"}. This record does not assert independent reproduction.

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