Triple
T10390891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Turbo |
E244888
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | David Soren |
E223085
|
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: David Soren | Statement: [Turbo, screenwriter, David Soren]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Soren Context triple: [Turbo, screenwriter, David Soren]
-
A.
David Soren
chosen
David Soren is a Canadian filmmaker and animator best known for directing the animated feature film "Captain Underpants: The First Epic Movie."
-
B.
Rob Carpenter
Rob Carpenter is a former NFL running back best known for his productive stints with the Houston Oilers and New York Giants in the late 1970s and early 1980s.
-
C.
Dave Harken
Dave Harken is the tyrannical, manipulative boss and main antagonist portrayed by Kevin Spacey in the dark comedy film "Horrible Bosses."
-
D.
Brian Reynolds
Brian Reynolds is a technology entrepreneur best known as a founder of the enterprise software company Micro Focus.
-
E.
Brian J. Reynolds
Brian J. Reynolds is a cinematographer best known for his work on the crime film "Gang Related."
- 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9b4f7d08190bcb16d3b4c8f22ad |
completed | April 7, 2026, 11:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d7fbae9a9c81908178fca68eb142b6 |
completed | April 9, 2026, 7:19 p.m. |
Created at: April 6, 2026, 12:06 p.m.