Triple
T9835571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sparkle (2012 film) |
E239090
|
entity |
| Predicate | starredActor |
P5563
|
FINISHED |
| Object | Derek Luke |
E201587
|
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: Derek Luke | Statement: [Sparkle (2012 film), starredActor, Derek Luke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Derek Luke Context triple: [Sparkle (2012 film), starredActor, Derek Luke]
-
A.
Derek Luke
chosen
Derek Luke is an American actor known for his breakout role in "Antwone Fisher" and performances in films like "Glory Road" and "Captain America: The First Avenger."
-
B.
Omar Epps
Omar Epps is an American actor and producer best known for his roles in films like "Love & Basketball" and the TV series "House."
-
C.
Michael Ealy
Michael Ealy is an American actor known for his roles in films like "Barbershop," "Think Like a Man," and "2 Fast 2 Furious," as well as various television series.
-
D.
Chandler James Jones
Chandler James Jones is an American professional football defensive end best known for his Pro Bowl career in the NFL with teams such as the New England Patriots and Arizona Cardinals.
-
E.
James T. Reid
James T. Reid was an architect best known for designing prominent early 20th-century buildings in San Francisco, including landmark hotels.
- 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_69ca84e314108190978324a4bdb959f8 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb339aa1c8190901d8e660cef49c5 |
completed | April 2, 2026, 12:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5c8f1a48190a4e7b6cda8ee88d5 |
completed | April 5, 2026, 3:23 a.m. |
Created at: March 30, 2026, 8:33 p.m.