Triple
T17362150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ann Dvorak |
E422094
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | Scarface |
—
|
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: Scarface | Statement: [Ann Dvorak, workedOn, Scarface]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scarface Context triple: [Ann Dvorak, workedOn, Scarface]
-
A.
Scarface
chosen
Scarface is the notorious nickname of American gangster Al Capone, one of the most infamous crime bosses of the Prohibition era.
-
B.
Scarface
Scarface is a 1983 crime drama film chronicling the violent rise and fall of Cuban immigrant drug lord Tony Montana in Miami’s cocaine underworld.
-
C.
Scarface
Scarface is a pioneering American rapper and member of the influential Houston group Geto Boys, known for his vivid storytelling and impact on Southern hip-hop.
-
D.
Scarface: The World Is Yours
Scarface: The World Is Yours is an action-adventure video game adaptation and alternate sequel to the 1983 film Scarface, allowing players to control Tony Montana in an open-world crime setting.
-
E.
The Legend of Scarface
The Legend of Scarface is a children's picture book retelling a traditional Native American tale, written by Robert D. San Souci and known for its rich storytelling and cultural detail.
- 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_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a4d6de88190b816b93ff5778157 |
completed | April 19, 2026, 2:13 a.m. |
Created at: April 10, 2026, 5:44 a.m.