Triple
T3622940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richie Roberts |
E76768
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object |
character Richie Roberts in the film "American Gangster"
The character Richie Roberts in the film "American Gangster" is a principled yet troubled New Jersey detective who relentlessly pursues Harlem drug kingpin Frank Lucas amid widespread police corruption in the 1970s.
|
E373738
|
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: character Richie Roberts in the film "American Gangster" | Statement: [Richie Roberts, basedOn, character Richie Roberts in the film "American Gangster"]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: character Richie Roberts in the film "American Gangster" Context triple: [Richie Roberts, basedOn, character Richie Roberts in the film "American Gangster"]
-
A.
Henry Hill in Goodfellas
Henry Hill in Goodfellas is the ambitious young mob associate whose rise and fall within the New York Mafia underworld drives the film’s narrative.
-
B.
Buddy Russo in The French Connection
Buddy Russo in *The French Connection* is a tough, streetwise New York City detective who partners with Popeye Doyle in the gritty pursuit of an international heroin smuggling ring.
-
C.
Sal Maroni in The Dark Knight
Sal Maroni in The Dark Knight is a powerful Gotham City mob boss who becomes a key figure in the criminal underworld’s clash with Batman and the rise of Harvey Dent as Two-Face.
-
D.
Mr. Orange in Reservoir Dogs
Mr. Orange is an undercover cop posing as a criminal in Quentin Tarantino’s heist film "Reservoir Dogs," whose concealed identity and divided loyalties drive much of the movie’s tension and tragedy.
-
E.
Arturo Braga in Fast & Furious
Arturo Braga in Fast & Furious is a powerful Mexican drug cartel leader and primary antagonist who orchestrates high-risk cross-border smuggling operations.
- 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: character Richie Roberts in the film "American Gangster" Triple: [Richie Roberts, basedOn, character Richie Roberts in the film "American Gangster"]
Generated description
The character Richie Roberts in the film "American Gangster" is a principled yet troubled New Jersey detective who relentlessly pursues Harlem drug kingpin Frank Lucas amid widespread police corruption in the 1970s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: character Richie Roberts in the film "American Gangster" Target entity description: The character Richie Roberts in the film "American Gangster" is a principled yet troubled New Jersey detective who relentlessly pursues Harlem drug kingpin Frank Lucas amid widespread police corruption in the 1970s.
-
A.
Henry Hill in Goodfellas
Henry Hill in Goodfellas is the ambitious young mob associate whose rise and fall within the New York Mafia underworld drives the film’s narrative.
-
B.
Buddy Russo in The French Connection
Buddy Russo in *The French Connection* is a tough, streetwise New York City detective who partners with Popeye Doyle in the gritty pursuit of an international heroin smuggling ring.
-
C.
Sal Maroni in The Dark Knight
Sal Maroni in The Dark Knight is a powerful Gotham City mob boss who becomes a key figure in the criminal underworld’s clash with Batman and the rise of Harvey Dent as Two-Face.
-
D.
Mr. Orange in Reservoir Dogs
Mr. Orange is an undercover cop posing as a criminal in Quentin Tarantino’s heist film "Reservoir Dogs," whose concealed identity and divided loyalties drive much of the movie’s tension and tragedy.
-
E.
Arturo Braga in Fast & Furious
Arturo Braga in Fast & Furious is a powerful Mexican drug cartel leader and primary antagonist who orchestrates high-risk cross-border smuggling operations.
- 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_69ad85dae2fc81908d1ceadbc6af0089 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc2bc79008190abe6900adcbda8de |
completed | March 8, 2026, 6:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b43320955c8190910c0f15c80f41f4 |
completed | March 13, 2026, 3:54 p.m. |
| NEDg | Description generation | batch_69b43705642881909c62b7363a4f3a12 |
completed | March 13, 2026, 4:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4379cd04c81909246747bcc357261 |
completed | March 13, 2026, 4:13 p.m. |
Created at: March 8, 2026, 3:23 p.m.