Triple
T20389271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Live Free or Die Hard |
E498042
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Michael Fottrell |
—
|
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 Fottrell | Statement: [Live Free or Die Hard, producer, Michael Fottrell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Fottrell Context triple: [Live Free or Die Hard, producer, Michael Fottrell]
-
A.
Michael Fottrell
chosen
Michael Fottrell is a film producer best known for his work on major action franchises, including entries in the Fast & Furious series.
-
B.
Michael Ferguson
Michael Ferguson is a television director known for his work on the British soap opera EastEnders.
-
C.
Matthew Fenton
Matthew Fenton is an actor known for his role in the British romantic comedy film "Run Fatboy Run."
-
D.
Keith Foulke
Keith Foulke is a former Major League Baseball relief pitcher best known as the Boston Red Sox closer who played a pivotal role in their 2004 World Series championship run.
-
E.
Brian Fawcett
Brian Fawcett was the son of British explorer Percy Fawcett, known mainly for his connection to his father's legendary Amazon expeditions and disappearance.
- 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6790e65a081909832855758fffd14 |
completed | April 20, 2026, 7:05 p.m. |
Created at: April 16, 2026, 11:28 a.m.