Triple
T19797968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Max Bialystock |
E475592
|
entity |
| Predicate | belongsToWorkOf |
P89906
|
FINISHED |
| Object | American cinema |
—
|
LITERAL FINISHED |
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: American cinema | Statement: [Max Bialystock, belongsToWorkOf, American cinema]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToWorkOf Context triple: [Max Bialystock, belongsToWorkOf, American cinema]
-
A.
associatedWithWorkOf
chosen
Indicates that one entity has a connection or involvement with the work, creation, or output produced by another entity.
-
B.
belongsToWorkBy
Indicates that something is part of, or associated with, a work that was created by a specific agent or creator.
-
C.
containsWorksFrom
Indicates that one entity includes or holds works that originate from or are created by another entity.
-
D.
associatedWithAuthorWork
Indicates a relationship where an author is connected to a work they created, contributed to, or are otherwise credited for.
-
E.
coverOfWorkBy
Indicates that one work is a cover version or performance of another work originally created by a specified creator or artist.
- F. None of above.
Provenance (3 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653c877288190b56ee7eedea710a3 |
completed | April 20, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69e5305858108190bbbfdb9ba3ab9f80 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:49 p.m.