Triple
T3216001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dan Aykroyd |
E67395
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Donna Dixon
Donna Dixon is an American actress and former model known for her roles in 1980s comedies and for her long career in film and television.
|
E343784
|
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: Donna Dixon | Statement: [Dan Aykroyd, spouse, Donna Dixon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donna Dixon Context triple: [Dan Aykroyd, spouse, Donna Dixon]
-
A.
Blenda Russell
Blenda Russell is a singer best known for performing the opening theme song of the classic American sitcom "Good Times."
-
B.
Cyndy Hall
Cyndy Hall is a member of the Hall family best known as the sister of American model and actress Jerry Hall.
-
C.
Donell Jones
Donell Jones is an American R&B singer, songwriter, and producer best known for smooth, soulful hits like "Where I Wanna Be" and "U Know What's Up."
-
D.
Debra Hill
Debra Hill was an American film producer and screenwriter best known for co-writing and producing influential horror films such as "Halloween" alongside John Carpenter.
-
E.
Dody Dorn
Dody Dorn is an American film editor known for her work on movies such as "Memento" and collaborations with directors like Christopher Nolan and David Ayer.
- 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: Donna Dixon Triple: [Dan Aykroyd, spouse, Donna Dixon]
Generated description
Donna Dixon is an American actress and former model known for her roles in 1980s comedies and for her long career in film and television.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Donna Dixon Target entity description: Donna Dixon is an American actress and former model known for her roles in 1980s comedies and for her long career in film and television.
-
A.
Blenda Russell
Blenda Russell is a singer best known for performing the opening theme song of the classic American sitcom "Good Times."
-
B.
Cyndy Hall
Cyndy Hall is a member of the Hall family best known as the sister of American model and actress Jerry Hall.
-
C.
Donell Jones
Donell Jones is an American R&B singer, songwriter, and producer best known for smooth, soulful hits like "Where I Wanna Be" and "U Know What's Up."
-
D.
Debra Hill
Debra Hill was an American film producer and screenwriter best known for co-writing and producing influential horror films such as "Halloween" alongside John Carpenter.
-
E.
Dody Dorn
Dody Dorn is an American film editor known for her work on movies such as "Memento" and collaborations with directors like Christopher Nolan and David Ayer.
- F. None of above. chosen
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_69ad858b8adc8190ad989712c87a476b |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adab096b588190b22e41a76263ae92 |
completed | March 8, 2026, 4:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2e826c50c8190a6e472e7a8862df2 |
completed | March 12, 2026, 4:21 p.m. |
| NEDg | Description generation | batch_69b2e8e42ecc8190b81d1b64f9fba0c1 |
completed | March 12, 2026, 4:25 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b2e954ec18819096f31feb9e985b6a |
completed | March 12, 2026, 4:27 p.m. |
Created at: March 8, 2026, 3:07 p.m.