Triple
T21899548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Blackening |
E540770
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Tracy Oliver |
—
|
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: Tracy Oliver | Statement: [The Blackening, screenwriter, Tracy Oliver]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tracy Oliver Context triple: [The Blackening, screenwriter, Tracy Oliver]
-
A.
Tracy Oliver
chosen
Tracy Oliver is an American screenwriter, producer, and director known for her work on hit projects like "Girls Trip" and the TV series "Harlem," often centering Black women’s experiences in comedy and drama.
-
B.
Tracey Walter
Tracey Walter is an American character actor known for his quirky, offbeat supporting roles in films such as "Repo Man," "Batman" (1989), and numerous collaborations with director Jonathan Demme.
-
C.
Tracy Kramer
Tracy Kramer is a film producer best known for producing the action-comedy movie "Money Talks."
-
D.
Tracy Maurice
Tracy Maurice is a visual artist and designer known for creating distinctive album artwork and visual identities for musicians and bands.
-
E.
Tracy Yerkes Thomas
Tracy Yerkes Thomas was an American mathematician known for his contributions to differential geometry and tensor analysis.
- 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_69e0c47b4e8c81908c8076eaa4c8e4f2 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fca2bf88190b2a5b912aa102513 |
completed | April 28, 2026, 8:59 p.m. |
Created at: April 16, 2026, 7:07 p.m.