Triple
T3149992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roger Ailes |
E65853
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Elizabeth Ailes
Elizabeth Ailes is an American publisher and former television executive best known as the widow of longtime Fox News chairman Roger Ailes.
|
E372856
|
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: Elizabeth Ailes | Statement: [Roger Ailes, spouse, Elizabeth Ailes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elizabeth Ailes Context triple: [Roger Ailes, spouse, Elizabeth Ailes]
-
A.
Mary Carr
Mary Carr was an American character actress of the silent and early sound film era, often cast as kindly maternal figures.
-
B.
Elizabeth Hanks
Elizabeth Hanks is an American actress and writer, known for her supporting roles in films like "Forrest Gump" and for being the daughter of actor Tom Hanks.
-
C.
Mary Stuart McHenry
Mary Stuart McHenry was the wife of American statesman and former U.S. Secretary of State James Baker.
-
D.
Elizabeth Stevens
Elizabeth Stevens is known as the daughter of the late U.S. Supreme Court Justice John Paul Stevens.
-
E.
Mary Powell
Mary Powell was the first wife of English poet John Milton, whose brief and troubled marriage to him influenced his later writings on divorce and marriage.
- 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: Elizabeth Ailes Triple: [Roger Ailes, spouse, Elizabeth Ailes]
Generated description
Elizabeth Ailes is an American publisher and former television executive best known as the widow of longtime Fox News chairman Roger Ailes.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Elizabeth Ailes Target entity description: Elizabeth Ailes is an American publisher and former television executive best known as the widow of longtime Fox News chairman Roger Ailes.
-
A.
Mary Carr
Mary Carr was an American character actress of the silent and early sound film era, often cast as kindly maternal figures.
-
B.
Elizabeth Hanks
Elizabeth Hanks is an American actress and writer, known for her supporting roles in films like "Forrest Gump" and for being the daughter of actor Tom Hanks.
-
C.
Mary Stuart McHenry
Mary Stuart McHenry was the wife of American statesman and former U.S. Secretary of State James Baker.
-
D.
Elizabeth Stevens
Elizabeth Stevens is known as the daughter of the late U.S. Supreme Court Justice John Paul Stevens.
-
E.
Mary Powell
Mary Powell was the first wife of English poet John Milton, whose brief and troubled marriage to him influenced his later writings on divorce and marriage.
- 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_69ad8584485081909ed529e890cadc4a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada5bf902c8190a490fa55e2dcecc0 |
completed | March 8, 2026, 4:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b432ebe354819097a4ddce7355b8db |
completed | March 13, 2026, 3:53 p.m. |
| NEDg | Description generation | batch_69b438eeedc48190a7db2459b5ddd564 |
completed | March 13, 2026, 4:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4394014648190bc03d643a771395c |
completed | March 13, 2026, 4:20 p.m. |
Created at: March 8, 2026, 3:05 p.m.