Triple
T1108459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rachel Watson |
E25538
|
entity |
| Predicate | filmPortrayalBy |
P22751
|
FINISHED |
| Object | Emily Blunt |
E4055
|
NE FINISHED |
How this triple was built (3 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: Emily Blunt | Statement: [Rachel Watson, filmPortrayalBy, Emily Blunt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emily Blunt Context triple: [Rachel Watson, filmPortrayalBy, Emily Blunt]
-
A.
Emily Blunt
chosen
Emily Blunt is a British actress known for her versatile performances in films such as "The Devil Wears Prada," "Edge of Tomorrow," "A Quiet Place," and "Mary Poppins Returns."
-
B.
Jessica Chastain
Jessica Chastain is an acclaimed American actress known for her versatile performances in films such as "Zero Dark Thirty," "The Help," and "Molly's Game."
-
C.
Keira Knightley
Keira Knightley is an English actress known for her roles in period dramas and major film franchises such as "Pirates of the Caribbean" and "Pride & Prejudice."
-
D.
Alicia Vikander
Alicia Vikander is a Swedish actress known for her acclaimed performances in films such as "Ex Machina," "The Danish Girl," and "Tomb Raider."
-
E.
Amy Adams
Amy Adams is an acclaimed American actress known for her versatility in both comedic and dramatic roles, including performances in films such as "Enchanted," "American Hustle," and "Arrival."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmPortrayalBy Context triple: [Rachel Watson, filmPortrayalBy, Emily Blunt]
-
A.
partOfFilmographyOf
Indicates that a work (such as a film, show, or role) is included in the body of screen-related works credited to a particular person.
-
B.
subjectOfFilm
chosen
Indicates that a person, character, or topic is the main focus or central topic depicted in a particular film.
-
C.
producedFilm
Indicates that one entity served as the producer (or production company) responsible for making or financing the creation of a particular film.
-
D.
filmDirectorOfAppearance
Indicates that a person served as the director for a specific appearance or segment within a film or audiovisual work.
-
E.
filmBase
Indicates the primary location or headquarters from which a film-related entity (such as a production, company, or operation) is based or operates.
- F. None of above.
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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b9e6134481909f348986a25f65c6 |
completed | March 1, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad58a2448c81909cb30e1a4400e1f3 |
completed | March 8, 2026, 11:08 a.m. |
| PD | Predicate disambiguation | batch_69a4b749e2a881909ef28745a7d2d917 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:43 p.m.