Triple
T11666242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pat Crowley |
E277254
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Ed Hookstratten
Ed Hookstratten was a prominent Hollywood talent agent known for representing major television and sports broadcasting personalities.
|
E939294
|
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: Ed Hookstratten | Statement: [Pat Crowley, spouse, Ed Hookstratten]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ed Hookstratten Context triple: [Pat Crowley, spouse, Ed Hookstratten]
-
A.
Dick Hantak
Dick Hantak is a former National Football League official best known for serving as the referee in Super Bowl XXVII.
-
B.
Richard Strout
Richard Strout is a central character in the film "In the Bedroom," whose violent actions drive the story’s tragic conflict.
-
C.
Buck Houghton
Buck Houghton was an American television producer best known for his work on the original series of The Twilight Zone.
-
D.
Steve Hooker
Steve Hooker is an Australian pole vaulter and Olympic gold medallist, best known for winning the men's pole vault at the 2008 Beijing Games.
-
E.
William Strickler
William Strickler was a roller coaster designer and builder known for constructing classic wooden coasters such as the Big Dipper at Blackpool Pleasure Beach.
- 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: Ed Hookstratten Triple: [Pat Crowley, spouse, Ed Hookstratten]
Generated description
Ed Hookstratten was a prominent Hollywood talent agent known for representing major television and sports broadcasting personalities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ed Hookstratten Target entity description: Ed Hookstratten was a prominent Hollywood talent agent known for representing major television and sports broadcasting personalities.
-
A.
Dick Hantak
Dick Hantak is a former National Football League official best known for serving as the referee in Super Bowl XXVII.
-
B.
Richard Strout
Richard Strout is a central character in the film "In the Bedroom," whose violent actions drive the story’s tragic conflict.
-
C.
Buck Houghton
Buck Houghton was an American television producer best known for his work on the original series of The Twilight Zone.
-
D.
Steve Hooker
Steve Hooker is an Australian pole vaulter and Olympic gold medallist, best known for winning the men's pole vault at the 2008 Beijing Games.
-
E.
William Strickler
William Strickler was a roller coaster designer and builder known for constructing classic wooden coasters such as the Big Dipper at Blackpool Pleasure Beach.
- 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a43f438081909da476294a057c38 |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef13a2f1dc8190bb9ca8879ef42e14 |
completed | April 27, 2026, 7:43 a.m. |
| NEDg | Description generation | batch_69ef3550fae881909246cd4cca047a19 |
completed | April 27, 2026, 10:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ef519f95488190b4b5a167aa930133 |
completed | April 27, 2026, 12:08 p.m. |
Created at: April 8, 2026, 9:39 p.m.