Triple
T22258231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shoot 'Em Up |
E550146
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Michael Davis |
—
|
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 Davis | Statement: [Shoot 'Em Up, writer, Michael Davis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Davis Context triple: [Shoot 'Em Up, writer, Michael Davis]
-
A.
Michael Davis
Michael Davis was an American bassist best known as a member of the influential proto-punk band MC5.
-
B.
Michael Davis
Michael Davis is an entrepreneur best known as a co-founder of Bomis, the web portal company that played a key role in the early development of Wikipedia.
-
C.
Michael Davis
Michael Davis is an American comic book artist, writer, and producer best known as one of the founding members of the influential, Black-owned comics company Milestone Media.
-
D.
Michael Davis
Michael Davis is an astronomer known for his role in the discovery of the millisecond pulsar PSR B1937+21, one of the fastest-spinning neutron stars ever observed.
-
E.
Michael Davis
chosen
Michael Davis is an American film director and screenwriter best known for his hyper-stylized action movie "Shoot 'Em Up."
- 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.