Triple
T20055137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aaron Donald |
E499308
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Donald
Donald is the surname of Aaron Donald, a dominant American football defensive tackle widely regarded as one of the greatest defensive players in NFL history.
|
E499308
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Donald | Statement: [Aaron Donald, familyName, Donald]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donald Context triple: [Aaron Donald, familyName, Donald]
-
A.
Donald
Donald is the given first name of American film producer Don Simpson, known for his work on blockbuster Hollywood movies in the 1980s and 1990s.
-
B.
Donald
Donald is the given first name of Don Drysdale, the Hall of Fame Major League Baseball pitcher known for his dominant career with the Los Angeles Dodgers.
-
C.
Donald
Donald is the given name of Lord Nicholls of Birkenhead, a prominent British judge and law lord known for his influential contributions to UK jurisprudence.
-
D.
Donald
Donald is the given first name of Don Hutson, a pioneering American football wide receiver widely regarded as one of the NFL’s earliest superstars.
-
E.
Donald
Donald is the given first name of American actor and singer Don Durant, known for his roles in mid-20th-century film and television.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Donald Triple: [Aaron Donald, familyName, Donald]
Generated description
Donald is the surname of Aaron Donald, a dominant American football defensive tackle widely regarded as one of the greatest defensive players in NFL history.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Donald Target entity description: Donald is the surname of Aaron Donald, a dominant American football defensive tackle widely regarded as one of the greatest defensive players in NFL history.
-
A.
Donald
chosen
Donald is the surname of Aaron Donald, the dominant American football defensive tackle widely regarded as one of the greatest defensive players in NFL history.
-
B.
Donald
Donald is the given first name of Don Hutson, a pioneering American football wide receiver widely regarded as one of the NFL’s earliest superstars.
-
C.
Donald
Donald is the given name of Donald David Coryell, the innovative American football coach known for revolutionizing the passing game in the NFL.
-
D.
Donald
Donald is the given name of Donald Trump, the 45th president of the United States and a prominent businessman and media personality.
-
E.
Donald
Donald is the given name of Don Revie, the renowned English football player and manager best known for his successful tenure at Leeds United.
- F. None of above.
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66332b300819097f5dca1636e5822 |
completed | April 20, 2026, 5:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a081f31fcd88190a7ad0461610ebf57 |
completed | May 16, 2026, 7:39 a.m. |
| NEDg | Description generation | batch_6a081fbb7f208190a032f9f312fd07de |
completed | May 16, 2026, 7:41 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08208c203c819083abea34d10d5e4e |
completed | May 16, 2026, 7:45 a.m. |
Created at: April 11, 2026, 3:38 p.m.