Triple
T17832627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Cashion |
E445298
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Jane Cashion |
—
|
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: Jane Cashion | Statement: [Red Cashion, spouse, Jane Cashion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jane Cashion Context triple: [Red Cashion, spouse, Jane Cashion]
-
A.
Jane Cashion
chosen
Jane Cashion is known as the wife of longtime NFL referee Red Cashion.
-
B.
Dorothy LaBostrie
Dorothy LaBostrie was an American songwriter best known for co-writing Little Richard’s landmark rock and roll hit “Tutti Frutti.”
-
C.
Laura Garrety
Laura Garrety is a central character in the dark comedy film "Very Bad Things," around whom much of the movie’s escalating chaos and moral collapse revolves.
-
D.
Jane Loring
Jane Loring was a film editor known for her work in early 20th-century American cinema.
-
E.
Mary Jane Paul
Mary Jane Paul is the ambitious, career-driven television news anchor and complex protagonist at the center of the drama series "Being Mary Jane."
- 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_69d8b9f1a6d881909f024bc603111cdb |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48d257414819088730f48ad7ab9ae |
completed | April 19, 2026, 8:07 a.m. |
Created at: April 10, 2026, 10:15 a.m.