Triple
T22633201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Big Lift |
E558608
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | George Seaton |
—
|
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: George Seaton | Statement: [The Big Lift, director, George Seaton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: George Seaton Context triple: [The Big Lift, director, George Seaton]
-
A.
George Seaton
chosen
George Seaton was an American screenwriter, director, and producer best known for films such as "Miracle on 34th Street" and "Airport."
-
B.
George Sewell
George Sewell was a British character actor known for his tough, often villainous roles in film and television during the 1960s and 1970s.
-
C.
Thomas Mayne
Thomas Mayne was an Australian food scientist best known for creating the chocolate malted milk drink Milo in the 1930s.
-
D.
Edward Kidner
Edward Kidner is the wealthy, terminally ill industrialist in the science fiction film "Self/less" whose consciousness is transferred into a younger body, setting off the movie’s central ethical and existential conflicts.
-
E.
John Seaton
John Seaton is a fictional character from the 1978 British-American sports drama film "International Velvet."
- 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_69e245467d9881908d6985bd0db7a1f1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1700ab4308190a16b0a1b2a0210fd |
completed | April 29, 2026, 2:42 a.m. |
Created at: April 17, 2026, 3:03 p.m.