Triple
T21956493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rogue (2007 film) |
E542200
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Greg McLean |
—
|
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: Greg McLean | Statement: [Rogue (2007 film), writer, Greg McLean]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greg McLean Context triple: [Rogue (2007 film), writer, Greg McLean]
-
A.
Greg McLean
chosen
Greg McLean is an Australian filmmaker best known as the writer-director of the horror film "Wolf Creek" and its sequels.
-
B.
Greg McLean
Greg McLean is a Canadian politician who served as a Conservative Member of Parliament representing a Calgary riding in Alberta.
-
C.
Michael Coulter
Michael Coulter is a British cinematographer known for his work on popular films including the romantic comedy "Love Actually."
-
D.
Nick McLean
Nick McLean is an American cinematographer best known for his work on popular films of the 1980s, including the adventure classic "The Goonies."
-
E.
Andrew Lesnie
Andrew Lesnie was an Australian cinematographer best known for his Oscar-winning work on Peter Jackson’s The Lord of the Rings film trilogy.
- 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_69e0c47ef0e48190a50e1bcc43f4b3fd |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f124404f38819080bae736a52a51cd |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:59 p.m.