Triple
T21373677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mission: Impossible |
E527135
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Bruce Geller |
—
|
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: Bruce Geller | Statement: [Mission: Impossible, creator, Bruce Geller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bruce Geller Context triple: [Mission: Impossible, creator, Bruce Geller]
-
A.
Bruce Geller
chosen
Bruce Geller was an American television producer, writer, and director best known for creating the iconic spy series "Mission: Impossible."
-
B.
Kevin Gimpel
Kevin Gimpel is a computer scientist and researcher in natural language processing and machine learning, known for his work on deep learning models for language understanding.
-
C.
Stan Gottlieb
Stan Gottlieb is an actor best known for his role in the 1969 satirical film "Putney Swope."
-
D.
Phil Greenberg
Phil Greenberg is an immunologist and biotech entrepreneur known for pioneering work in cancer immunotherapy and co-founding Juno Therapeutics.
-
E.
Michael Gottlieb
Michael Gottlieb was an American film director and screenwriter best known for directing the 1987 fantasy comedy "Mannequin" and other lighthearted Hollywood comedies.
- 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_69e0b51e80808190ba5cb05667af02a9 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b0b248508190aebeb671e55198da |
completed | April 22, 2026, 11:27 a.m. |
Created at: April 16, 2026, 5:10 p.m.