Triple
T32606368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saratoga (1937 film) |
E833531
|
entity |
| Predicate | leadCharacterPlayedByClarkGable |
P174932
|
FINISHED |
| Object | Duke Bradley |
—
|
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: Duke Bradley | Statement: [Saratoga (1937 film), leadCharacterPlayedByClarkGable, Duke Bradley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leadCharacterPlayedByClarkGable Context triple: [Saratoga (1937 film), leadCharacterPlayedByClarkGable, Duke Bradley]
-
A.
humphreyBogartRole
Indicates that one entity is a role or character portrayed by Humphrey Bogart in a film, play, or other performance.
-
B.
hasGingerRogersRole
Indicates that an entity is assigned or associated with a role specifically identified as the "Ginger Rogers" role in a given context or production.
-
C.
portrayedIn1953FilmBy
Indicates that an entity (typically a person or character) was depicted or played by another entity in a film released in the year 1953.
-
D.
hasGlennFordRole
Indicates that an entity has a role played by the actor Glenn Ford.
-
E.
AvaGardnerRole
Indicates that an entity represents a role or character portrayed by Ava Gardner in a film, television production, or other performance.
- F. None of above. chosen
Provenance (4 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_69f3492bfa648190b6ae472074634e29 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c90790788190a1ed09adc86ed22d |
completed | May 3, 2026, 4:03 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f42fbc8190a06eb1044c9e6094 |
completed | May 3, 2026, 3:41 a.m. |
| PDg | Predicate description generation | batch_69f6c814c26c81908f5c47285129ff2a |
completed | May 3, 2026, 3:59 a.m. |
Created at: May 1, 2026, 1:05 a.m.