Triple
T21994099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Small Time Crooks |
E543159
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Steven Bernstein |
—
|
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: Steven Bernstein | Statement: [Small Time Crooks, musicBy, Steven Bernstein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steven Bernstein Context triple: [Small Time Crooks, musicBy, Steven Bernstein]
-
A.
Steven Bernstein
chosen
Steven Bernstein is an American trumpeter, composer, and bandleader known for his work in jazz and film scores.
-
B.
Steven Bernstein
Steven Bernstein is a cinematographer and film director known for his work on feature films such as the comedy "White Chicks."
-
C.
Adam Bernstein
Adam Bernstein is an American director best known for his work on influential music videos and acclaimed television series such as "Fargo" and "30 Rock."
-
D.
Jim Bernstein
Jim Bernstein is a television writer and producer best known for co-creating the Disney XD superhero-themed comedy series "Mighty Med."
-
E.
Joseph Bernstein
Joseph Bernstein is a prominent mathematician known for his influential work in representation theory, algebraic geometry, and number theory.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127639bf48190800b3fa3c1527983 |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 16, 2026, 8:17 p.m.