Triple
T25444013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Actor for Midnight Cowboy |
E637580
|
entity |
| Predicate | filmSettingState |
P52439
|
FINISHED |
| Object | Texas |
—
|
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: Texas | Statement: [Academy Award for Best Actor for Midnight Cowboy, filmSettingState, Texas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmSettingState Context triple: [Academy Award for Best Actor for Midnight Cowboy, filmSettingState, Texas]
-
A.
filmSetting
chosen
Indicates the place, time, or environment in which the events of a film are set or take place.
-
B.
filmAbilityChange
Indicates that a film’s capabilities or attributes (such as format, quality, or features) are altered from one state to another.
-
C.
filmingState
Indicates the current production or recording status of a filming activity, such as whether it is planned, in progress, paused, or completed.
-
D.
stateOfFilming
Indicates the location or jurisdiction (such as a state or region) where the filming of a work takes place.
-
E.
filmSettingTheater
Indicates that a film’s setting or key scenes take place in a theater (such as a cinema or playhouse).
- 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_69e75db6c97081908178383fa632b193 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f7028a5c8190b32720973dd5f45e |
completed | May 2, 2026, 1:07 p.m. |
| PD | Predicate disambiguation | batch_69f4683b34748190818428489a226124 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 2 p.m.