Triple
T16296515
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leave Her to Heaven |
E395660
|
entity |
| Predicate | cinematographyBy |
P1953
|
FINISHED |
| Object | Leon Shamroy |
E218746
|
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: Leon Shamroy | Statement: [Leave Her to Heaven, cinematographyBy, Leon Shamroy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leon Shamroy Context triple: [Leave Her to Heaven, cinematographyBy, Leon Shamroy]
-
A.
Leon Shamroy
chosen
Leon Shamroy was an acclaimed American cinematographer, renowned for his work on numerous Hollywood classics and for winning multiple Academy Awards during the mid-20th century.
-
B.
Joel Zimmerman
Joel Zimmerman is a film editor best known for his work on the 2000 horror film "Shadow of the Vampire."
-
C.
Maty Siman
Maty Siman is a technology entrepreneur best known as the founder of the application security company Checkmarx.
-
D.
Grant Shaud
Grant Shaud is an American actor best known for playing the high-strung news producer Miles Silverberg on the television sitcom "Murphy Brown."
-
E.
Kenny Aaronson
Kenny Aaronson is an American rock bassist and session musician known for his work with numerous bands and artists since the 1970s.
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e25e2dcdac819083918f0964dd5666 |
completed | April 17, 2026, 4:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a001f9b42248190a3c8c2647a42aeb9 |
completed | May 10, 2026, 6:03 a.m. |
Created at: April 10, 2026, 5:06 a.m.