Triple
T22412972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anastasia (1997 film) |
E554037
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Amy Pell |
—
|
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: Amy Pell | Statement: [Anastasia (1997 film), producer, Amy Pell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amy Pell Context triple: [Anastasia (1997 film), producer, Amy Pell]
-
A.
Amy Pell
chosen
Amy Pell is a film producer best known for her work on the animated musical feature "Anastasia" (1997).
-
B.
Amy Wheeler
Amy Wheeler is the protagonist of the Netflix limited series "From Scratch," an American woman whose cross-cultural romance and personal journey drive the show's emotional narrative.
-
C.
Amy Burley
Amy Burley is a free-spirited, V-addicted drifter who becomes Jason Stackhouse’s intense and ultimately tragic love interest in the TV series "True Blood."
-
D.
Amy Veness
Amy Veness was a British character actress known for her numerous supporting roles in early- to mid-20th-century films and stage productions.
-
E.
Petra Collins
Petra Collins is a Canadian artist, photographer, and filmmaker known for her dreamy, feminist visual style in fashion, art, and music videos.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e4e6ce8819085a1e06d886bf21c |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1594496348190ba25dc0193d092f2 |
completed | April 29, 2026, 1:05 a.m. |
Created at: April 16, 2026, 8:46 p.m.