Triple
T22803675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marmaduke (2010 film) |
E564470
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Tom Dey |
—
|
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: Tom Dey | Statement: [Marmaduke (2010 film), director, Tom Dey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Dey Context triple: [Marmaduke (2010 film), director, Tom Dey]
-
A.
Tom Dey
chosen
Tom Dey is an American film director best known for helming the Jackie Chan and Owen Wilson action-comedy "Shanghai Noon."
-
B.
Dan Goor
Dan Goor is an American television writer and producer best known for co-creating the comedy series "Brooklyn Nine-Nine" and his work on shows like "Parks and Recreation."
-
C.
Vance Powell
Vance Powell is a Grammy-winning American record producer, engineer, and mixer known for his work with artists across rock, country, and alternative music.
-
D.
Darius Marder
Darius Marder is an American filmmaker and screenwriter best known for co-writing the crime drama "The Place Beyond the Pines" and directing the acclaimed film "Sound of Metal."
-
E.
Jesse Harlin
Jesse Harlin is a video game music composer known for his work on major titles including The Sims 4.
- 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_69e245823f4c8190ade442cdcc2c224a |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17d5a7c2881909a7aaacddd09f00c |
completed | April 29, 2026, 3:39 a.m. |
Created at: April 17, 2026, 3:31 p.m.