Triple
T20269725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winnie Holzman |
E499061
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Paul Dooley |
—
|
NE NERFINISHED |
How this triple was built (2 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: Paul Dooley | Statement: [Winnie Holzman, spouse, Paul Dooley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Dooley Context triple: [Winnie Holzman, spouse, Paul Dooley]
-
A.
Paul Dooley
chosen
Paul Dooley is an American character actor, writer, and comedian known for his roles in films such as "Breaking Away," "Sixteen Candles," and numerous television series.
-
B.
Leo Willis
Leo Willis was an American character actor active during the silent and early sound film eras, often appearing in comedies alongside stars like Harold Lloyd.
-
C.
Jeffery Wood
Jeffery Wood is an American actor best known for his role on the television sitcom "In the House."
-
D.
Ray Wise
Ray Wise is an American character actor known for his versatile roles in film and television, including memorable performances in "Twin Peaks," "RoboCop," and numerous other genre and dramatic works.
-
E.
Dennis Morgan
Dennis Morgan was an American film actor and singer best known for his leading-man roles in Hollywood musicals and dramas of the 1940s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da6275fa6c8190952924930adee150 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e675dc8e708190b840d687f134c9e8 |
completed | April 20, 2026, 6:52 p.m. |
Created at: April 11, 2026, 11:42 p.m.