Triple
T14046212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bulletproof |
E337962
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object |
Erik Ron
Erik Ron is a music producer and songwriter known for his work with rock and alternative bands, including composing for the song "Bulletproof."
|
E1076654
|
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: Erik Ron | Statement: [Bulletproof, composer, Erik Ron]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erik Ron Context triple: [Bulletproof, composer, Erik Ron]
-
A.
Steve Koren
Steve Koren is an American comedy writer and screenwriter known for his work on films like "A Night at the Roxbury" and for writing on "Saturday Night Live."
-
B.
Dusty Boggess
Dusty Boggess was a prominent Major League Baseball umpire who officiated in multiple World Series during the mid-20th century.
-
C.
Mike Gunton
Mike Gunton is a British television producer best known for his work on landmark BBC natural history documentaries.
-
D.
Jack Briggs
Jack Briggs was an American actor best known for his marriage to Hollywood star Ginger Rogers.
-
E.
Joe Rohde
Joe Rohde is an American creative executive and former Walt Disney Imagineer best known for leading the design of Disney’s Animal Kingdom and other highly themed, story-driven attractions.
- 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: Erik Ron Triple: [Bulletproof, composer, Erik Ron]
Generated description
Erik Ron is a music producer and songwriter known for his work with rock and alternative bands, including composing for the song "Bulletproof."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Erik Ron Target entity description: Erik Ron is a music producer and songwriter known for his work with rock and alternative bands, including composing for the song "Bulletproof."
-
A.
Steve Koren
Steve Koren is an American comedy writer and screenwriter known for his work on films like "A Night at the Roxbury" and for writing on "Saturday Night Live."
-
B.
Dusty Boggess
Dusty Boggess was a prominent Major League Baseball umpire who officiated in multiple World Series during the mid-20th century.
-
C.
Mike Gunton
Mike Gunton is a British television producer best known for his work on landmark BBC natural history documentaries.
-
D.
Jack Briggs
Jack Briggs was an American actor best known for his marriage to Hollywood star Ginger Rogers.
-
E.
Joe Rohde
Joe Rohde is an American creative executive and former Walt Disney Imagineer best known for leading the design of Disney’s Animal Kingdom and other highly themed, story-driven attractions.
- 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de312df37081909f45ce3e219af5dc |
completed | April 14, 2026, 12:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbc34148348190a8c67e035646e431 |
completed | May 6, 2026, 10:40 p.m. |
| NEDg | Description generation | batch_69fc4300948881908784c5ad99188ad2 |
completed | May 7, 2026, 7:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fc444630408190b368611373265973 |
completed | May 7, 2026, 7:50 a.m. |
Created at: April 9, 2026, 10:20 p.m.