Triple
T16230959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Duplass |
E393977
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Duplass |
E315754
|
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: Duplass | Statement: [Mark Duplass, familyName, Duplass]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Duplass Context triple: [Mark Duplass, familyName, Duplass]
-
A.
Lawrence Duplass
Lawrence Duplass is a member of the Duplass family, related to American filmmaker and actor Jay Duplass.
-
B.
Jay Duplass
chosen
Jay Duplass is an American filmmaker and actor known for his work in independent cinema and television, often collaborating with his brother Mark Duplass.
-
C.
Frances Ha
Frances Ha is a 2012 black-and-white indie comedy-drama film directed by Noah Baumbach and co-written by and starring Greta Gerwig, following a young woman’s aimless yet hopeful life in New York City.
-
D.
Apatow
Apatow is the surname most prominently associated with American filmmaker and comedy producer Judd Apatow and his family.
-
E.
Farrelly
Farrelly is a surname most prominently associated with American filmmaker Peter Farrelly, known for his work on hit comedy films.
- 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_69d87f204df88190a8f88923decf9835 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e23d29438c81909aa2724cc47bb959 |
completed | April 17, 2026, 2:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0007a0ab08819082aea4c312c9ffc7 |
completed | May 10, 2026, 4:20 a.m. |
Created at: April 10, 2026, 5:03 a.m.