Triple
T17496516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ernest Dickerson |
E426074
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Bulletproof |
—
|
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: Bulletproof | Statement: [Ernest Dickerson, notableWork, Bulletproof]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bulletproof Context triple: [Ernest Dickerson, notableWork, Bulletproof]
-
A.
Bulletproof
"Bulletproof" is a hard rock song by the American band Godsmack, released as a single from their 2018 album "When Legends Rise."
-
B.
Bulletproof
chosen
Bulletproof is a 1996 American buddy action-comedy film starring Damon Wayans and Adam Sandler, known for mixing slapstick humor with crime and undercover-cop themes.
-
C.
Bulletproof
Bulletproof is a film featuring Filipino actor Cesar Montano in a prominent role.
-
D.
Bulletproof
"Bulletproof" is a memoir by reality TV personality Maci Bookout that chronicles her experiences with teen pregnancy, fame, and personal growth.
-
E.
Bulletproof
"Bulletproof" is a synth-pop song by English duo La Roux, fronted by Elly Jackson, that became a major international hit in 2009.
- 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_69d889dccf7481909264a1844a2e9100 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4520e9c8c8190aa955766bc915d26 |
completed | April 19, 2026, 3:54 a.m. |
Created at: April 10, 2026, 5:48 a.m.