Triple
T1008896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve Wozniak |
E21775
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Candice Clark
Candice Clark is an American former slalom canoeist and the ex-wife of Apple co-founder Steve Wozniak.
|
E217502
|
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: Candice Clark | Statement: [Steve Wozniak, spouse, Candice Clark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Candice Clark Context triple: [Steve Wozniak, spouse, Candice Clark]
-
A.
Amanda Clifton
Amanda Clifton is an American sports executive and advocate best known as the wife of WNBA star Elena Delle Donne and for her work promoting women’s basketball and LGBTQ+ visibility.
-
B.
Amanda Clayton
Amanda Clayton is an American actress best known for her role in the crime drama television series "City on a Hill."
-
C.
Nicole Shanahan
Nicole Shanahan is an American attorney, legal tech entrepreneur, and philanthropist known for founding the patent management company ClearAccessIP and for her high-profile marriage to Google co-founder Sergey Brin.
-
D.
Megan Holley
Megan Holley is an American screenwriter best known for writing the indie dramedy film "Sunshine Cleaning."
-
E.
Erin McDermott
Erin McDermott is a collegiate sports administrator best known as the athletic director at Harvard University.
- 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: Candice Clark Triple: [Steve Wozniak, spouse, Candice Clark]
Generated description
Candice Clark is an American former slalom canoeist and the ex-wife of Apple co-founder Steve Wozniak.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Candice Clark Target entity description: Candice Clark is an American former slalom canoeist and the ex-wife of Apple co-founder Steve Wozniak.
-
A.
Amanda Clifton
Amanda Clifton is an American sports executive and advocate best known as the wife of WNBA star Elena Delle Donne and for her work promoting women’s basketball and LGBTQ+ visibility.
-
B.
Amanda Clayton
Amanda Clayton is an American actress best known for her role in the crime drama television series "City on a Hill."
-
C.
Nicole Shanahan
Nicole Shanahan is an American attorney, legal tech entrepreneur, and philanthropist known for founding the patent management company ClearAccessIP and for her high-profile marriage to Google co-founder Sergey Brin.
-
D.
Megan Holley
Megan Holley is an American screenwriter best known for writing the indie dramedy film "Sunshine Cleaning."
-
E.
Erin McDermott
Erin McDermott is a collegiate sports administrator best known as the athletic director at Harvard University.
- 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_69a493c53e648190ae8cb76c433fd9a7 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b7a2186c819081a495bc15f8c7fd |
completed | March 1, 2026, 10:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adf3a5cac081908d655e42a58a81c5 |
completed | March 8, 2026, 10:09 p.m. |
| NEDg | Description generation | batch_69adf55207248190bd903c7faa3729e7 |
completed | March 8, 2026, 10:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69adf5e074088190b6b383fb93cd18d8 |
completed | March 8, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:41 p.m.