Triple
T22258340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Ice Road |
E550149
|
entity |
| Predicate | cinematographyBy |
P1953
|
FINISHED |
| Object | Tom Stern |
—
|
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: Tom Stern | Statement: [The Ice Road, cinematographyBy, Tom Stern]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Stern Context triple: [The Ice Road, cinematographyBy, Tom Stern]
-
A.
Tom Stern
chosen
Tom Stern is an American cinematographer best known for his frequent collaborations with director Clint Eastwood on numerous acclaimed films.
-
B.
Tom Stern
Tom Stern is a screenwriter best known for co-writing the 1997 horror-comedy film "An American Werewolf in Paris."
-
C.
Jonathan Stern
Jonathan Stern is an American film and television producer best known for his work on offbeat comedies such as "Wet Hot American Summer" and various projects for Adult Swim and streaming platforms.
-
D.
Ben Schulberg
Ben Schulberg was an American film producer and studio executive active during the early Hollywood era.
-
E.
Mike Kellerman
Mike Kellerman is a fictional Baltimore homicide detective known for his morally complex investigations and personal struggles on the television series "Homicide: Life on the Street."
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138c4bff48190b4be83f5f7677ac8 |
completed | April 28, 2026, 10:46 p.m. |
Created at: April 16, 2026, 8:39 p.m.