Triple
T20241707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Replacement Killers |
E498311
|
entity |
| Predicate | mainProtagonist |
P9202
|
FINISHED |
| Object | John Lee |
—
|
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: John Lee | Statement: [The Replacement Killers, mainProtagonist, John Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Lee Context triple: [The Replacement Killers, mainProtagonist, John Lee]
-
A.
John Lee
John Lee is a film editor known for his work on the superhero movie "Black Adam."
-
B.
John Lee
chosen
John Lee is the skilled professional assassin portrayed by Chow Yun-fat in the 1998 action film "The Replacement Killers."
-
C.
John Lee
John Lee was an American statesman who represented South Carolina as a delegate to the Continental Congress during the Revolutionary era.
-
D.
John Griffith Lee
John Griffith Lee was the husband of acclaimed American actress Agnes Moorehead, known for her work in film, radio, and television.
-
E.
James Kang
James Kang is a film producer best known for his work on the family martial-arts comedy movie "Three Ninjas."
- 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6716eabf48190ae4e760f472114bd |
completed | April 20, 2026, 6:33 p.m. |
Created at: April 11, 2026, 11:40 p.m.