Triple
T22448195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vampire Academy (2014 film) |
E554917
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Mark Waters |
—
|
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: Mark Waters | Statement: [Vampire Academy (2014 film), director, Mark Waters]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Waters Context triple: [Vampire Academy (2014 film), director, Mark Waters]
-
A.
Mark Waters
chosen
Mark Waters is an American film director best known for helming popular teen and fantasy comedies such as "Mean Girls" and "Freaky Friday."
-
B.
Mark Waters
Mark Waters is an American musician best known as a member of the punk rock band F.Y.P.
-
C.
Judd Apatow
Judd Apatow is an American filmmaker, producer, and writer known for his influential work in modern comedy films and television series such as "The 40-Year-Old Virgin," "Knocked Up," and "Freaks and Geeks."
-
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.
Nicholas Stoller
Nicholas Stoller is a British-American filmmaker and screenwriter best known for directing and writing popular comedy films such as Forgetting Sarah Marshall and Neighbors.
- 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b48be0481909f4601b732424e5b |
completed | April 29, 2026, 1:13 a.m. |
Created at: April 16, 2026, 8:48 p.m.