Triple
T12374355
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Quiet Little Marriage |
E295083
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object |
Mo Perkins
Mo Perkins is an American filmmaker best known for her independent drama film "A Quiet Little Marriage."
|
E979350
|
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: Mo Perkins | Statement: [A Quiet Little Marriage, director, Mo Perkins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mo Perkins Context triple: [A Quiet Little Marriage, director, Mo Perkins]
-
A.
Ian Perkins
Ian Perkins is a British guitarist best known for his work with The Horrible Crowes, the side project of The Gaslight Anthem’s Brian Fallon.
-
B.
Justin Perkins
Justin Perkins is an American musician and producer best known for his work in punk rock, including playing bass for the influential band Screeching Weasel.
-
C.
Ann Perkins
Ann Perkins is a compassionate and pragmatic nurse who becomes Leslie Knope’s best friend and a central figure in the sitcom "Parks and Recreation."
-
D.
Chris Perkel
Chris Perkel is a film editor and director best known for his work on music-related documentaries, including the Clive Davis biographical film "Clive Davis: The Soundtrack of Our Lives."
-
E.
Neil Perry
Neil Perry is an American local politician who serves as the mayor of Methuen, Massachusetts.
- 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: Mo Perkins Triple: [A Quiet Little Marriage, director, Mo Perkins]
Generated description
Mo Perkins is an American filmmaker best known for her independent drama film "A Quiet Little Marriage."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mo Perkins Target entity description: Mo Perkins is an American filmmaker best known for her independent drama film "A Quiet Little Marriage."
-
A.
Ian Perkins
Ian Perkins is a British guitarist best known for his work with The Horrible Crowes, the side project of The Gaslight Anthem’s Brian Fallon.
-
B.
Justin Perkins
Justin Perkins is an American musician and producer best known for his work in punk rock, including playing bass for the influential band Screeching Weasel.
-
C.
Ann Perkins
Ann Perkins is a compassionate and pragmatic nurse who becomes Leslie Knope’s best friend and a central figure in the sitcom "Parks and Recreation."
-
D.
Chris Perkel
Chris Perkel is a film editor and director best known for his work on music-related documentaries, including the Clive Davis biographical film "Clive Davis: The Soundtrack of Our Lives."
-
E.
Neil Perry
Neil Perry is an American local politician who serves as the mayor of Methuen, Massachusetts.
- 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_69d6ab6d8a4081908636601e69ddf262 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93fa8ca7c8190b3f8e9c2ec23e837 |
completed | April 10, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62ac1e82c8190abb46ca5799e6680 |
completed | May 2, 2026, 4:48 p.m. |
| NEDg | Description generation | batch_69f62ef1cc4481909bc9fc768a9ef1f2 |
completed | May 2, 2026, 5:05 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f62f808b1481908f529decdbfc5be6 |
completed | May 2, 2026, 5:08 p.m. |
Created at: April 8, 2026, 9:54 p.m.