Triple
T30190639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Dunson |
E767469
|
entity |
| Predicate | filmCharacterOf |
P168523
|
FINISHED |
| Object | Howard Hawks |
—
|
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: Howard Hawks | Statement: [Thomas Dunson, filmCharacterOf, Howard Hawks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmCharacterOf Context triple: [Thomas Dunson, filmCharacterOf, Howard Hawks]
-
A.
directorCharacterOf
Indicates that a director is responsible for directing a particular character in a work (e.g., film, TV show, or play).
-
B.
characterInFilmReleasedIn
Indicates that a character appears in a film that was released in a specified year or time period.
-
C.
filmSeriesProtagonistOf
Indicates that a character serves as the main recurring protagonist of a particular film series.
-
D.
filmAssociatedWith
Indicates a general relationship or connection between a film and another entity, such as a person, organization, event, or work.
-
E.
featuresCharactersFrom
Indicates that one entity (such as a work or production) includes or presents characters originating from another entity.
- 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_69f2247cc3d88190811dec3face94bf5 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67f8393948190aa6fc6acea2e7d00 |
completed | May 2, 2026, 10:49 p.m. |
| PD | Predicate disambiguation | batch_69f673c7a4588190837854f3ef61e6bf |
completed | May 2, 2026, 9:59 p.m. |
| PDg | Predicate description generation | batch_69f6749f205c81909d1aacf462912eee |
completed | May 2, 2026, 10:03 p.m. |
Created at: April 29, 2026, 7:28 p.m.