Triple
T19416018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Sundowners |
E485717
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | The Sundowners |
—
|
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: The Sundowners | Statement: [The Sundowners, title, The Sundowners]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Sundowners Context triple: [The Sundowners, title, The Sundowners]
-
A.
The Sundowners
chosen
The Sundowners is a 1960 adventure drama film set in the Australian outback, starring Robert Mitchum and Deborah Kerr as itinerant sheep drovers.
-
B.
Sundowner
Sundowner is a historic British motor yacht famed for its role in the 1940 Dunkirk evacuation, where it helped rescue Allied troops from the beaches of France.
-
C.
Sundown
"Sundown" is a song by Bruce Springsteen featured on his 2019 studio album *Western Stars*.
-
D.
Sundown
"Sundown" is a 1974 folk-rock song by Canadian singer-songwriter Gordon Lightfoot, widely recognized as one of his biggest hits.
-
E.
Sunset in the Blue
"Sunset in the Blue" is a jazz album by American singer-songwriter Melody Gardot, showcasing her smooth vocals and romantic, orchestral arrangements.
- 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_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e62af9c8fc81909860de10b6720207 |
completed | April 20, 2026, 1:32 p.m. |
Created at: April 10, 2026, 1:37 p.m.