Triple
T4060616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Phelps |
E86200
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Nicole Johnson
Nicole Johnson is an American model and former Miss California USA best known as the wife of Olympic swimmer Michael Phelps.
|
E521548
|
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: Nicole Johnson | Statement: [Michael Phelps, spouse, Nicole Johnson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nicole Johnson Context triple: [Michael Phelps, spouse, Nicole Johnson]
-
A.
Nicole Willis
Nicole Willis is a central character in the thriller film "Mindhunters," portrayed as one of the FBI profiler trainees trapped on a remote island during a deadly training exercise.
-
B.
Nicole Young
Nicole Young is an American attorney best known as the longtime former wife of hip-hop producer and entrepreneur Dr. Dre.
-
C.
Nicole Powell
Nicole Powell is a former standout American basketball player and WNBA All-Star who became a successful collegiate women’s basketball coach.
-
D.
Nicole Parker
Nicole Parker is an American actress and comedian best known for her sketch work on MADtv and roles in parody films.
-
E.
Nikki Butler
Nikki Butler is an American fashion designer best known for her long-term marriage to English actor Tim Roth.
- 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: Nicole Johnson Triple: [Michael Phelps, spouse, Nicole Johnson]
Generated description
Nicole Johnson is an American model and former Miss California USA best known as the wife of Olympic swimmer Michael Phelps.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Nicole Johnson Target entity description: Nicole Johnson is an American model and former Miss California USA best known as the wife of Olympic swimmer Michael Phelps.
-
A.
Nicole Willis
Nicole Willis is a central character in the thriller film "Mindhunters," portrayed as one of the FBI profiler trainees trapped on a remote island during a deadly training exercise.
-
B.
Nicole Young
Nicole Young is an American attorney best known as the longtime former wife of hip-hop producer and entrepreneur Dr. Dre.
-
C.
Nicole Powell
Nicole Powell is a former standout American basketball player and WNBA All-Star who became a successful collegiate women’s basketball coach.
-
D.
Nicole Parker
Nicole Parker is an American actress and comedian best known for her sketch work on MADtv and roles in parody films.
-
E.
Nikki Butler
Nikki Butler is an American fashion designer best known for her long-term marriage to English actor Tim Roth.
- 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_69aed93c69208190a4efac0efe3cd69b |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefbd32c0c8190bc575974ccf831b3 |
completed | March 9, 2026, 4:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf41063b048190a68a6f6d42b7aaa2 |
completed | March 22, 2026, 1:08 a.m. |
| NEDg | Description generation | batch_69bf43db7fa48190b58fe5a5d7509cb8 |
completed | March 22, 2026, 1:20 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf4475e86481909de41b6fa7959c8f |
completed | March 22, 2026, 1:23 a.m. |
Created at: March 9, 2026, 3:38 p.m.