Triple
T14854606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adventureland |
E349318
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Matt Bush |
E976908
|
NE FINISHED |
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: Matt Bush | Statement: [Adventureland, portrayedBy, Matt Bush]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Bush Context triple: [Adventureland, portrayedBy, Matt Bush]
-
A.
Matt Bush
chosen
Matt Bush is an American actor known for his roles in films like "Adventureland" and "Piranha 3D" as well as various television series and commercials.
-
B.
Jeff Bushell
Jeff Bushell is an American screenwriter best known for his work on the family comedy film "Beverly Hills Chihuahua."
-
C.
Todd Busch
Todd Busch is a film editor best known for his work on the 1997 superhero horror film "Spawn."
-
D.
Michael Buckley
Michael Buckley is a common name shared by several notable individuals, including authors, entertainers, and public figures across different fields.
-
E.
Rob Buckley
Rob Buckley is a relatively obscure individual whose name is notably associated with the surname Buckley but who has no widely recognized public profile.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d822ed7e1881909b90fca143ad7e34 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded44318f0819080b6c599f2d3474f |
completed | April 14, 2026, 11:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fec870cea08190962434fc2647fd67 |
completed | May 9, 2026, 5:38 a.m. |
Created at: April 10, 2026, 1:54 a.m.