Triple
T16648561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ingrid Bergman as Alicia Huberman |
E404540
|
entity |
| Predicate | filmNationality |
P55618
|
FINISHED |
| Object | American |
—
|
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 | Statement: [Ingrid Bergman as Alicia Huberman, filmNationality, American]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmNationality Context triple: [Ingrid Bergman as Alicia Huberman, filmNationality, American]
-
A.
filmCountryOfOrigin
Indicates the country where a film was originally produced or created.
-
B.
nationalCinema
chosen
Indicates that a film or cinematic work is associated with, produced by, or representative of a particular nation’s cinema.
-
C.
hasDirectorNationality
Indicates that the nationality of a director is associated with a given entity (such as a film, organization, or work).
-
D.
filmingCountry
Indicates the country where the filming or primary production of a work took place.
-
E.
film
Indicates that an entity is a movie or cinematic work, or that a relationship involves such a movie.
- 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_69d8838a41f08190b0c3f79c47df5078 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37ad794388190b2817d2ec5ff0de0 |
completed | April 18, 2026, 12:36 p.m. |
| PD | Predicate disambiguation | batch_69e319b1d7f08190b5ecb4a68c636c15 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:18 a.m.