Triple
T20901212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reign of the Supermen (film) |
E514670
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Sam Liu |
—
|
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: Sam Liu | Statement: [Reign of the Supermen (film), director, Sam Liu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sam Liu Context triple: [Reign of the Supermen (film), director, Sam Liu]
-
A.
Sam Liu
chosen
Sam Liu is an American animation director best known for his extensive work on DC Comics animated films and television series.
-
B.
Young Liu
Young Liu is a Taiwanese business executive best known as the chairman of Foxconn, the world’s largest electronics manufacturing services provider.
-
C.
Ernest Liu
Ernest Liu is an American actor best known for his role as Scott Fuller in the horror film "From Dusk Till Dawn."
-
D.
William Li
William Li is a Chinese entrepreneur best known as the founder and CEO of the electric vehicle company NIO.
-
E.
John Cheng
John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
- 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_69e0b4f8a1108190bce3d31331290ced |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6e8fc5d488190b62f51c35e768d38 |
completed | April 21, 2026, 3:03 a.m. |
Created at: April 16, 2026, 12:47 p.m.