Triple
T3009756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American Hustle |
E81987
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
Megan Ellison
Megan Ellison is an American film producer and founder of Annapurna Pictures, known for backing acclaimed independent and auteur-driven films such as "Her," "Zero Dark Thirty," and "American Hustle."
|
E318087
|
NE FINISHED |
How this triple was built (4 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: Megan Ellison | Statement: [American Hustle, producer, Megan Ellison]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Megan Ellison Context triple: [American Hustle, producer, Megan Ellison]
-
A.
Amy Pascal
Amy Pascal is an American film producer and former Sony Pictures executive known for overseeing and producing numerous major Hollywood films.
-
B.
Thomas Grazer
Thomas Grazer is the son of acclaimed American film and television producer Brian Grazer.
-
C.
Jane Kurson
Jane Kurson is a film editor best known for her work on the 1988 fantasy-comedy film "Beetlejuice."
-
D.
Amanda Silver
Amanda Silver is an American screenwriter and producer best known for co-writing major blockbuster films such as Jurassic World and the Avatar sequels.
-
E.
Amanda Iger
Amanda Iger is one of the children of longtime Disney CEO and media executive Bob Iger.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Megan Ellison Triple: [American Hustle, producer, Megan Ellison]
Generated description
Megan Ellison is an American film producer and founder of Annapurna Pictures, known for backing acclaimed independent and auteur-driven films such as "Her," "Zero Dark Thirty," and "American Hustle."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Megan Ellison Target entity description: Megan Ellison is an American film producer and founder of Annapurna Pictures, known for backing acclaimed independent and auteur-driven films such as "Her," "Zero Dark Thirty," and "American Hustle."
-
A.
Amy Pascal
Amy Pascal is an American film producer and former Sony Pictures executive known for overseeing and producing numerous major Hollywood films.
-
B.
Thomas Grazer
Thomas Grazer is the son of acclaimed American film and television producer Brian Grazer.
-
C.
Jane Kurson
Jane Kurson is a film editor best known for her work on the 1988 fantasy-comedy film "Beetlejuice."
-
D.
Amanda Silver
Amanda Silver is an American screenwriter and producer best known for co-writing major blockbuster films such as Jurassic World and the Avatar sequels.
-
E.
Amanda Iger
Amanda Iger is one of the children of longtime Disney CEO and media executive Bob Iger.
- F. None of above. chosen
Provenance (5 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_69ad8b1c4de88190a83b7cefaa1f2842 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a4ccbf08190a7580c9e758804d0 |
completed | March 8, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b12e5f612c8190824deb0813a9f981 |
completed | March 11, 2026, 8:57 a.m. |
| NEDg | Description generation | batch_69b12eec384881908e6bbb6b52a3f607 |
completed | March 11, 2026, 8:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b1ca54a5ec8190b8f35119ae23051f |
completed | March 11, 2026, 8:02 p.m. |
Created at: March 8, 2026, 3 p.m.