Triple
T13434701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paranoid Park |
E320199
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object | Amy Duddleston |
E455202
|
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: Amy Duddleston | Statement: [Paranoid Park, editor, Amy Duddleston]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amy Duddleston Context triple: [Paranoid Park, editor, Amy Duddleston]
-
A.
Amy Dromey
Amy Dromey is the daughter of British Labour politician Harriet Harman and trade unionist Jack Dromey.
-
B.
Shannon Doughton
Shannon Doughton is a musician best known as a principal performer associated with the band Pod.
-
C.
Rachel McCleary
Rachel McCleary is an American economist and scholar known for her work on the intersection of religion, culture, and economic development.
-
D.
Christine Roulston
Christine Roulston is a Canadian academic and scholar, known for her work in French studies and gender/sexuality studies and as the long-term partner of author Emma Donoghue.
-
E.
Amy E. Duddleston
chosen
Amy E. Duddleston is an American film editor known for her work on major studio features and acclaimed television series.
- 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_69d80761e6cc8190a90c844589998ecc |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbaee29fec81908b07b4fca2922242 |
completed | April 12, 2026, 2:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff3d3551cc8190848c14c15da07dc4 |
completed | May 9, 2026, 1:57 p.m. |
Created at: April 9, 2026, 9:40 p.m.