Triple
T20398305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gentlemen Marry Brunettes |
E500264
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Scott Brady |
—
|
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: Scott Brady | Statement: [Gentlemen Marry Brunettes, castMember, Scott Brady]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scott Brady Context triple: [Gentlemen Marry Brunettes, castMember, Scott Brady]
-
A.
Scott Brady
chosen
Scott Brady was an American film and television actor known for his rugged roles in Westerns and crime dramas during the mid-20th century.
-
B.
Scott Brady
Scott Brady is the child of Sarah Brady, known primarily in relation to her.
-
C.
Jack Brady
Jack Brady is a fictional character from the romantic comedy film "Leap Year."
-
D.
John Brady
John Brady is an American college basketball coach best known for leading the LSU Tigers men's basketball program, including a run to the NCAA Final Four in 2006.
-
E.
Ed Brady
Ed Brady was an American character actor of the early 20th century who appeared in numerous Hollywood films, often in supporting or uncredited roles.
- 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_69e0b4a81bec8190b69adfdc1336a015 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6798c2b28819092fab93f01218cde |
completed | April 20, 2026, 7:07 p.m. |
Created at: April 16, 2026, 11:29 a.m.