Triple
T20035089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rain (1928 film) |
E497234
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Luther Reed |
—
|
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: Luther Reed | Statement: [Rain (1928 film), screenwriter, Luther Reed]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Luther Reed Context triple: [Rain (1928 film), screenwriter, Luther Reed]
-
A.
Luther Reed
chosen
Luther Reed was an American film director and screenwriter active in the early 20th century, known for his work on several Hollywood musicals and dramas.
-
B.
Luther Allison
Luther Allison was an acclaimed American blues guitarist and singer known for his powerful performances and significant influence on modern electric blues.
-
C.
Leroy Fair
Leroy Fair was an original member of The Contours, the Motown vocal group best known for their hit "Do You Love Me."
-
D.
Willie Reed
Willie Reed is an American professional basketball player and center who has played in the NBA and its developmental leagues, known for his rebounding and shot-blocking abilities.
-
E.
Guymon Casady
Guymon Casady is an American film and television producer and talent manager, known for his work on projects such as "Office Christmas Party" and the series "Game of Thrones."
- 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_69da627278c88190babe4297a9df1236 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e662e76f8481909c006921cbbfd060 |
completed | April 20, 2026, 5:31 p.m. |
Created at: April 11, 2026, 3:36 p.m.