Triple
T9936952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Girl, Interrupted |
E193982
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object |
Angelina Jolie as Lisa Rowe
Angelina Jolie as Lisa Rowe is Jolie’s acclaimed, Oscar-winning portrayal of a charismatic, sociopathic patient in the 1999 psychological drama film "Girl, Interrupted."
|
E831344
|
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: Angelina Jolie as Lisa Rowe | Statement: [Girl, Interrupted, portrayedBy, Angelina Jolie as Lisa Rowe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angelina Jolie as Lisa Rowe Context triple: [Girl, Interrupted, portrayedBy, Angelina Jolie as Lisa Rowe]
-
A.
Virginia Madsen as Katherine
Virginia Madsen as Katherine refers to the actress’s role as a key human ally drawn into the celestial conflict between angels in the 1995 supernatural thriller film "The Prophecy."
-
B.
Laura Dern as Delilah
Laura Dern as Delilah is a supporting character in the film "Everything Must Go," portrayed by Laura Dern as a compassionate figure who briefly enters the protagonist’s life and offers him empathy and perspective during his personal crisis.
-
C.
Julia Roberts as Julianne Potter
Julia Roberts as Julianne Potter is the charming yet conflicted lead character in the romantic comedy "My Best Friend's Wedding," known for scheming to win back her longtime friend before his wedding.
-
D.
Lieutenant Marta Robbins – Jennifer Esposito
Lieutenant Marta Robbins, portrayed by Jennifer Esposito in the 2004 action-comedy film "Taxi," is a tough, no-nonsense New York police lieutenant who often clashes with the film’s bumbling protagonist.
-
E.
Nicole Kidman as Patti Lomax
Nicole Kidman as Patti Lomax is the compassionate and resilient wife of Eric Lomax in the film "The Railway Man," supporting him as he confronts the trauma of his World War II experiences.
- 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: Angelina Jolie as Lisa Rowe Triple: [Girl, Interrupted, portrayedBy, Angelina Jolie as Lisa Rowe]
Generated description
Angelina Jolie as Lisa Rowe is Jolie’s acclaimed, Oscar-winning portrayal of a charismatic, sociopathic patient in the 1999 psychological drama film "Girl, Interrupted."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Angelina Jolie as Lisa Rowe Target entity description: Angelina Jolie as Lisa Rowe is Jolie’s acclaimed, Oscar-winning portrayal of a charismatic, sociopathic patient in the 1999 psychological drama film "Girl, Interrupted."
-
A.
Virginia Madsen as Katherine
Virginia Madsen as Katherine refers to the actress’s role as a key human ally drawn into the celestial conflict between angels in the 1995 supernatural thriller film "The Prophecy."
-
B.
Laura Dern as Delilah
Laura Dern as Delilah is a supporting character in the film "Everything Must Go," portrayed by Laura Dern as a compassionate figure who briefly enters the protagonist’s life and offers him empathy and perspective during his personal crisis.
-
C.
Julia Roberts as Julianne Potter
Julia Roberts as Julianne Potter is the charming yet conflicted lead character in the romantic comedy "My Best Friend's Wedding," known for scheming to win back her longtime friend before his wedding.
-
D.
Lieutenant Marta Robbins – Jennifer Esposito
Lieutenant Marta Robbins, portrayed by Jennifer Esposito in the 2004 action-comedy film "Taxi," is a tough, no-nonsense New York police lieutenant who often clashes with the film’s bumbling protagonist.
-
E.
Nicole Kidman as Patti Lomax
Nicole Kidman as Patti Lomax is the compassionate and resilient wife of Eric Lomax in the film "The Railway Man," supporting him as he confronts the trauma of his World War II experiences.
- 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_69ca82e409348190a393777356b80a2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5e4e19881909879b394090d6629 |
completed | April 2, 2026, 12:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d228e7247c81908dbba76199f2e93f |
completed | April 5, 2026, 9:18 a.m. |
| NEDg | Description generation | batch_69d22a2831348190909b9507edfe49f3 |
completed | April 5, 2026, 9:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d22af8914c8190a8116a37a42b633c |
completed | April 5, 2026, 9:27 a.m. |
Created at: March 30, 2026, 8:44 p.m.