Triple
T12358220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harold & Kumar Go to White Castle |
E294665
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Greg Shapiro |
E442752
|
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: Greg Shapiro | Statement: [Harold & Kumar Go to White Castle, producer, Greg Shapiro]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greg Shapiro Context triple: [Harold & Kumar Go to White Castle, producer, Greg Shapiro]
-
A.
Greg Shapiro
chosen
Greg Shapiro is an American film producer best known for his Academy Award-winning work on "The Hurt Locker" and other notable independent and studio films.
-
B.
Craig Shapiro
Craig Shapiro is a television writer and producer best known for co-creating and showrunning series such as the sci-fi drama "Salvation."
-
C.
Andrew Weisblum
Andrew Weisblum is an American film editor known for his work on major feature films, including collaborations with directors like Darren Aronofsky and Wes Anderson.
-
D.
Todd Lieberman
Todd Lieberman is an American film producer known for his work on acclaimed movies such as "The Fighter" and other major Hollywood productions.
-
E.
Mark Shapiro
Mark Shapiro is an American media executive and sports industry leader who serves as president and a top decision-maker at Endeavor Group Holdings.
- 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_69d6ab6d8a4081908636601e69ddf262 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f8e64dc81908c2242c68cd1b86e |
completed | April 10, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f64b90779881909893d1e6877ce567 |
completed | May 2, 2026, 7:08 p.m. |
Created at: April 8, 2026, 9:54 p.m.