Triple
T18073460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Black Dakotas |
E432491
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Aaron Stell |
—
|
NE NERFINISHED |
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: Aaron Stell | Statement: [The Black Dakotas, editedBy, Aaron Stell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aaron Stell Context triple: [The Black Dakotas, editedBy, Aaron Stell]
-
A.
Aaron Stell
chosen
Aaron Stell was an American film editor known for his work on numerous Hollywood features and television productions.
-
B.
Aaron Stecker
Aaron Stecker is a former American football running back best known for his NFL career with teams like the Tampa Bay Buccaneers and New Orleans Saints.
-
C.
Aaron Burckhard
Aaron Burckhard is an American drummer best known as one of the earliest drummers for the grunge band Nirvana during its formative years.
-
D.
Aaron Stockard
Aaron Stockard is an American screenwriter best known for co-writing the acclaimed crime drama film "Gone Baby Gone" with Ben Affleck.
-
E.
Matthew Stuecken
Matthew Stuecken is a film screenwriter best known for co-writing the psychological sci-fi thriller "10 Cloverfield Lane."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9070cac81909fa9473fb1c3f1c7 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ccefcdc4819086d0b224731bfc4d |
completed | April 19, 2026, 12:39 p.m. |
Created at: April 10, 2026, 10:26 a.m.