Triple
T20885142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neverwas |
E514257
|
entity |
| Predicate | cinematographyBy |
P1953
|
FINISHED |
| Object | Michael Coulter |
—
|
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 Coulter | Statement: [Neverwas, cinematographyBy, Michael Coulter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Coulter Context triple: [Neverwas, cinematographyBy, Michael Coulter]
-
A.
Michael Coulter
chosen
Michael Coulter is a British cinematographer known for his work on popular films including the romantic comedy "Love Actually."
-
B.
Jason Collett
Jason Collett is a Canadian singer-songwriter and guitarist best known as a member of the indie rock collective Broken Social Scene and for his solo folk-rock work.
-
C.
Christian Corry
Christian Corry is an American former U.S. Marine Corps helicopter pilot best known as the husband of legendary soccer player Mia Hamm.
-
D.
Eric Campbell
Eric Campbell was a Scottish-born silent film actor best known for playing imposing comic villains alongside Charlie Chaplin in early 20th-century comedies.
-
E.
Thomas Coulter
Thomas Coulter was a 19th-century Irish physician, botanist, and explorer known for his plant collections in Mexico and the southwestern United States.
- 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c67c9d1c81908031eb77c124f119 |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 12:46 p.m.