Triple
T20386798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul |
E497980
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Greg Mottola |
—
|
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: Greg Mottola | Statement: [Paul, director, Greg Mottola]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greg Mottola Context triple: [Paul, director, Greg Mottola]
-
A.
Gregory Mottola
chosen
Gregory Mottola is an American film director and screenwriter best known for directing the comedy films "Superbad" and "Adventureland."
-
B.
Jason Reitman
Jason Reitman is a Canadian-American filmmaker known for his sharp, character-driven comedies and dramas such as "Juno," "Up in the Air," and "Thank You for Smoking."
-
C.
Josh Abrahams
Josh Abrahams is an Australian electronic music producer and composer known for his work in film, television, and video games.
-
D.
Mike Sikowitz
Mike Sikowitz is a television writer and producer best known for his work on sitcoms such as "Dr. Ken" and contributions to other popular comedy series.
-
E.
Dan Heder
Dan Heder is an American visual effects artist and the twin brother of actor Jon Heder.
- 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6790bcef481909453d19c846ab420 |
completed | April 20, 2026, 7:05 p.m. |
Created at: April 16, 2026, 11:28 a.m.