Triple
T21210941
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mini-Me |
E522715
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Michael McCullers |
—
|
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: Michael McCullers | Statement: [Mini-Me, creator, Michael McCullers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael McCullers Context triple: [Mini-Me, creator, Michael McCullers]
-
A.
Michael McCullers
chosen
Michael McCullers is an American screenwriter best known for his work on comedy films such as the Austin Powers series and various animated features.
-
B.
Michael McCusker
Michael McCusker is an American film editor known for his work on major Hollywood productions, including the thriller "The Girl on the Train" (2016).
-
C.
Jeffrey Himes
Jeffrey Himes is a musician best known for having been a past member of the indie rock band Okkervil River.
-
D.
Mark McCorkle
Mark McCorkle is an American television writer and producer best known as the co-creator of the animated series "Kim Possible" and for his work on various other animated projects.
-
E.
Christopher Collins
Christopher Collins is a television producer best known for his work on Anthony Bourdain’s acclaimed travel and food documentary series.
- 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_69e0b5112d8881909510b2dcdc93106d |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7346eb20c8190aeb3c0cc0a24aaf9 |
completed | April 21, 2026, 8:25 a.m. |
Created at: April 16, 2026, 3:37 p.m.