Triple
T13516708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Undoing |
E322778
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Noah Jupe |
E131397
|
NE 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: Noah Jupe | Statement: [The Undoing, starring, Noah Jupe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Noah Jupe Context triple: [The Undoing, starring, Noah Jupe]
-
A.
Noah Jupe
chosen
Noah Jupe is a British actor known for his acclaimed performances as a child and teen in films such as "A Quiet Place," "Honey Boy," and "Ford v Ferrari."
-
B.
Isaac Hempstead Wright
Isaac Hempstead Wright is an English actor best known for portraying Bran Stark in the HBO fantasy television series Game of Thrones.
-
C.
Fionn Whitehead
Fionn Whitehead is a British actor best known for his breakout leading role in Christopher Nolan’s World War II film "Dunkirk."
-
D.
Rupert Friend
Rupert Friend is an English actor known for roles in films like "Pride & Prejudice" and the TV series "Homeland."
-
E.
Harris Dickinson
Harris Dickinson is a British actor known for his roles in films such as "The King’s Man," "Beach Rats," and "Triangle of Sadness."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d80766a21881909f21a1b7421d3b8a |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbafa0ed508190b2855171b1945e84 |
completed | April 12, 2026, 2:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c0d759fc81908c327850a4836ecd |
completed | May 3, 2026, 9:40 p.m. |
Created at: April 9, 2026, 9:44 p.m.