Triple
T6278438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glitter |
E140718
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Vondie Curtis-Hall |
E177110
|
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: Vondie Curtis-Hall | Statement: [Glitter, director, Vondie Curtis-Hall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vondie Curtis-Hall Context triple: [Glitter, director, Vondie Curtis-Hall]
-
A.
Vondie Curtis-Hall
chosen
Vondie Curtis-Hall is an American actor and filmmaker known for his work in film and television, both in front of and behind the camera.
-
B.
Wanya Morris
Wanya Morris is an American R&B singer best known as a member of the vocal group Boyz II Men.
-
C.
Dominique McElligott
Dominique McElligott is an Irish actress known for her roles in television series such as Hell on Wheels, House of Cards, and The Boys.
-
D.
Ruby Aldridge
Ruby Aldridge is an American fashion model known for her runway and editorial work with major designers and magazines.
-
E.
Yvette Wilson
Yvette Wilson was an American comedian and actress best known for her role as Andell Wilkerson on the sitcoms "Moesha" and its spin-off "The Parkers."
- 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_69c008cc158881908df6ec94a911c736 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063daec108190859d1d5dbafd5b42 |
completed | March 22, 2026, 9:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c5194e9b3881908188f004c4a03a09 |
completed | March 26, 2026, 11:32 a.m. |
Created at: March 22, 2026, 4:26 p.m.