Triple
T23530869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Windom |
E576564
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Carol Keyser
Carol Keyser is known as the former spouse of American actor William Windom.
|
E1592104
|
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: Carol Keyser | Statement: [William Windom, spouse, Carol Keyser]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carol Keyser Context triple: [William Windom, spouse, Carol Keyser]
-
A.
Elizabeth Kaye
Elizabeth Kaye was an English noblewoman best known as the wife of Francis North, 1st Earl of Guilford, a prominent 17th-century lawyer and statesman.
-
B.
Carol Kenney
Carol Kenney is the optimistic, late-in-life medical intern and main character portrayed by Patricia Heaton in the sitcom "Carol's Second Act."
-
C.
Claire Keesey
Claire Keesey is a Boston bank manager who becomes romantically involved with a career criminal, unaware of his role in the heist that traumatized her, in the film "The Town."
-
D.
Laura Rister
Laura Rister is a film producer and executive known for her work on independent and prestige projects, including the financial thriller "Margin Call."
-
E.
Elizabeth Reaser
Elizabeth Reaser is an American actress best known for her roles in the Twilight film series and the television drama Grey's Anatomy.
- 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: Carol Keyser Triple: [William Windom, spouse, Carol Keyser]
Generated description
Carol Keyser is known as the former spouse of American actor William Windom.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Carol Keyser Target entity description: Carol Keyser is known as the former spouse of American actor William Windom.
-
A.
Elizabeth Kaye
Elizabeth Kaye was an English noblewoman best known as the wife of Francis North, 1st Earl of Guilford, a prominent 17th-century lawyer and statesman.
-
B.
Carol Kenney
Carol Kenney is the optimistic, late-in-life medical intern and main character portrayed by Patricia Heaton in the sitcom "Carol's Second Act."
-
C.
Claire Keesey
Claire Keesey is a Boston bank manager who becomes romantically involved with a career criminal, unaware of his role in the heist that traumatized her, in the film "The Town."
-
D.
Laura Rister
Laura Rister is a film producer and executive known for her work on independent and prestige projects, including the financial thriller "Margin Call."
-
E.
Elizabeth Reaser
Elizabeth Reaser is an American actress best known for her roles in the Twilight film series and the television drama Grey's Anatomy.
- 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_69e245f5a8848190a2ba42e271c6c31f |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1ac7759e88190aea55c65e24c081f |
completed | April 29, 2026, 7 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0cdf559a988190926f6f2ae298da58 |
completed | May 19, 2026, 10:08 p.m. |
| NEDg | Description generation | batch_6a0d7213f9508190a8884846e19079e3 |
completed | May 20, 2026, 8:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0d72ad1b148190bbe5f65e84ac2837 |
completed | May 20, 2026, 8:37 a.m. |
Created at: April 17, 2026, 6:09 p.m.