Triple
T3934457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seth Rogen |
E90874
|
entity |
| Predicate | appearedInFilm |
P795
|
FINISHED |
| Object | The Green Hornet |
E399719
|
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: The Green Hornet | Statement: [Seth Rogen, appearedInFilm, The Green Hornet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Green Hornet Context triple: [Seth Rogen, appearedInFilm, The Green Hornet]
-
A.
The Green Hornet
chosen
The Green Hornet is a 2011 action-comedy superhero film based on the classic radio and TV character, featuring a wealthy playboy who becomes a masked crime-fighter with his skilled sidekick Kato.
-
B.
G-Men
G-Men is a popular nickname for the New York Giants, the professional American football team based in the New York metropolitan area.
-
C.
The Mysterious Mr. Wong
The Mysterious Mr. Wong is a 1934 American mystery film featuring Bela Lugosi as a sinister Chinatown crime lord seeking power through a series of murders.
-
D.
Heroes for Hire
Heroes for Hire is a Marvel Comics superhero team that operates as a for-profit crime-fighting and protection agency, often featuring street-level heroes like Luke Cage and Iron Fist.
-
E.
The Bat
The Bat is a popular inverted boomerang-style roller coaster at Canada's Wonderland known for its intense forward and backward loops.
- 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_69aed95f26e0819094b0e71974543a19 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeedcbf0188190a5e828707a77752a |
completed | March 9, 2026, 3:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5338afa348190bc5ac0b0319c6e45 |
completed | March 14, 2026, 10:08 a.m. |
Created at: March 9, 2026, 3:23 p.m.