Triple
T10395003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank (2014 film) |
E244987
|
entity |
| Predicate | cinematographyBy |
P1953
|
FINISHED |
| Object | James Mather |
E854683
|
NE FINISHED |
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: James Mather | Statement: [Frank (2014 film), cinematographyBy, James Mather]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: James Mather Context triple: [Frank (2014 film), cinematographyBy, James Mather]
-
A.
James Mather
chosen
James Mather is a film director best known for co-directing the 2012 science fiction action movie "Lockout."
-
B.
James Warren Sever
James Warren Sever was a Harvard University alumnus and benefactor after whom the historic Sever Hall in Harvard Yard is named.
-
C.
John Davenport
John Davenport was a prominent 17th-century English Puritan clergyman and co-founder of the New Haven Colony in New England.
-
D.
Victor Peirce
Victor Peirce was an Australian career criminal and prominent member of Melbourne’s notorious Pettingill crime family, long linked to drug trafficking, armed robbery, and gangland violence.
-
E.
Lowell Mather
Lowell Mather is a lovable, dim-witted but mechanically gifted airport handyman and comic relief character from the television sitcom "Wings."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9ce6bb08190bfeaba98a126526d |
completed | April 7, 2026, 11:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9987838ac8190a6ba09305fc27621 |
completed | April 11, 2026, 12:40 a.m. |
Created at: April 6, 2026, 12:06 p.m.