Triple
T22838328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fred Schepisi |
E566006
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mary Schepisi |
—
|
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: Mary Schepisi | Statement: [Fred Schepisi, spouse, Mary Schepisi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Schepisi Context triple: [Fred Schepisi, spouse, Mary Schepisi]
-
A.
Mary Schepisi
chosen
Mary Schepisi is an American artist and painter known for her contemporary works and for being married to Australian film director Fred Schepisi.
-
B.
Rhonda Schepisi
Rhonda Schepisi is the wife of Australian film director Fred Schepisi.
-
C.
Alexandra Schepisi
Alexandra Schepisi is an Australian actress and occasional director known for her work in film, television, and theatre.
-
D.
Gillian Armstrong
Gillian Armstrong is an Australian film director best known for works such as "My Brilliant Career" and the 1994 adaptation of "Little Women."
-
E.
Jocelyn Moorhouse
Jocelyn Moorhouse is an Australian film director and screenwriter known for character-driven dramas such as "Proof" and "How to Make an American Quilt."
- 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_69e245869e188190a196584f36e682da |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e8244dc819089c0a7525fb512ab |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:35 p.m.