Triple
T29148527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Supporting Actress for Up in the Air |
E738837
|
entity |
| Predicate | filmThemes |
P120580
|
FINISHED |
| Object | corporate downsizing |
—
|
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: corporate downsizing | Statement: [Academy Award for Best Supporting Actress for Up in the Air, filmThemes, corporate downsizing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmThemes Context triple: [Academy Award for Best Supporting Actress for Up in the Air, filmThemes, corporate downsizing]
-
A.
filmThemeConnection
chosen
Indicates a relationship where a film is associated with, explores, or is centered around a particular theme.
-
B.
fictionalTheme
Indicates that a work, element, or context is centered around or characterized by a fictional theme or motif.
-
C.
themeOfWinningFilm
Indicates that the subject is the central topic or theme depicted in the film that has won a particular award or competition.
-
D.
filmType
Indicates the specific category or genre that a film belongs to.
-
E.
dramaticTheme
Indicates that a work, scene, or narrative centers around a particular dramatic subject, motif, or emotional conflict as its main thematic focus.
- 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_69f07cb46f148190874eb8576a447567 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f662a362088190b474e822a96086e8 |
completed | May 2, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:41 a.m.