Triple
T21899619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Marshall |
E540772
|
entity |
| Predicate | relationshipRoleInFilm |
P146104
|
FINISHED |
| Object | ex-girlfriend of protagonist |
—
|
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: ex-girlfriend of protagonist | Statement: [Sarah Marshall, relationshipRoleInFilm, ex-girlfriend of protagonist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipRoleInFilm Context triple: [Sarah Marshall, relationshipRoleInFilm, ex-girlfriend of protagonist]
-
A.
roleInFilmEcosystem
Indicates the specific function or position an entity holds within the broader network of activities, stakeholders, and processes that make up the film ecosystem.
-
B.
characterActorRelationship
Indicates a relationship where an actor portrays or is associated with a specific character in a work.
-
C.
has part in role
Indicates that an entity participates as a component or constituent specifically in a defined role within a larger whole or process.
-
D.
givenNameInFilm
Indicates that a person is referred to by a particular given (first) name within the context of a specific film.
-
E.
bondActorInFilm
Indicates that the person is an actor who has portrayed the character James Bond in a film.
- 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_69e0c47b4e8c81908c8076eaa4c8e4f2 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fca2bf88190b2a5b912aa102513 |
completed | April 28, 2026, 8:59 p.m. |
| PD | Predicate disambiguation | batch_69e6be9a65888190a66598d62d20366c |
completed | April 21, 2026, 12:02 a.m. |
| PDg | Predicate description generation | batch_69e6d054737081908aa7112975b77475 |
completed | April 21, 2026, 1:18 a.m. |
Created at: April 16, 2026, 7:07 p.m.