Triple
T22654274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stealing Fire |
E559181
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Jon Goldsmith |
—
|
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: Jon Goldsmith | Statement: [Stealing Fire, producer, Jon Goldsmith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jon Goldsmith Context triple: [Stealing Fire, producer, Jon Goldsmith]
-
A.
Jonathan Goldsmith
chosen
Jonathan Goldsmith is a Canadian composer best known for his film and television scores.
-
B.
Jonathan Goldsmith
Jonathan Goldsmith is an American actor best known for playing the charismatic, bearded spokesman in Dos Equis beer commercials as “The Most Interesting Man in the World.”
-
C.
Joel Goldsmith
Joel Goldsmith was an American composer best known for his work on film and television scores, including the Stargate franchise.
-
D.
Gary Goldman
Gary Goldman is an American screenwriter best known for his work on major science fiction and action films, including the 1990 movie "Total Recall."
-
E.
Gary Goldman
Gary Goldman is an American animator, director, and producer best known for his work on Don Bluth–style animated films such as Anastasia.
- 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_69e245489dd88190b1f674acf61c8769 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1765a97ac819095f21ccbdada1d0a |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 3:06 p.m.