Triple
T22663797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ma (2019 film) |
E559729
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | John Norris |
—
|
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: John Norris | Statement: [Ma (2019 film), producer, John Norris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Norris Context triple: [Ma (2019 film), producer, John Norris]
-
A.
John Norris
chosen
John Norris is a film producer known for his work on projects such as the 2019 drama "Ma."
-
B.
John Norris
John Norris was an English Elizabethan soldier and general noted for his campaigns in Ireland and on the Continent, and for leading the failed 1589 English Armada against Spain.
-
C.
Ken Norris
Ken Norris was a British engineer best known for designing record-breaking high-speed hydroplanes and land-speed vehicles, including Donald Campbell’s Bluebird K7.
-
D.
Ken Norris
Ken Norris was a pioneering marine mammalogist and educator best known for his influential work in dolphin research and marine park development.
-
E.
Mike Norris
Mike Norris is an American actor and director best known as the son of martial artist and film star Chuck Norris and for his roles in action and faith-based films.
- 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_69e2454a158c819093b8e35f5045efb6 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f176617ed8819095a58a2c9f1e3918 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 3:08 p.m.