Triple
T4419298
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King Kong (2005 film) |
E95057
|
entity |
| Predicate | cinematography |
P1953
|
FINISHED |
| Object | Andrew Lesnie |
E102049
|
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: Andrew Lesnie | Statement: [King Kong (2005 film), cinematography, Andrew Lesnie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Lesnie Context triple: [King Kong (2005 film), cinematography, Andrew Lesnie]
-
A.
Andrew Lesnie
chosen
Andrew Lesnie was an Australian cinematographer best known for his Oscar-winning work on Peter Jackson’s The Lord of the Rings film trilogy.
-
B.
John Linson
John Linson is an American film and television producer best known for creating the series Yellowstone and producing projects like Sons of Anarchy.
-
C.
Neil Hartley
Neil Hartley is a film and television producer known for his work on the adaptation of "The Go-Between."
-
D.
Greg Lansing
Greg Lansing is an American college basketball coach best known for his tenure as head coach of the Indiana State Sycamores men's basketball program.
-
E.
Michael Andrews
Michael Andrews is an American film composer and musician known for his atmospheric scores for movies such as Donnie Darko and Bridesmaids.
- 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_69b3453a36908190b95a79a297ca083c |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3551e7c6c819090fa5dfb5ac58e4c |
completed | March 13, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b65f34df20819090767fe4c577be87 |
completed | March 15, 2026, 7:26 a.m. |
Created at: March 12, 2026, 11:29 p.m.