Triple
T15012774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andre Dubus |
E377878
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Patricia Dubus |
E1131688
|
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: Patricia Dubus | Statement: [Andre Dubus, spouse, Patricia Dubus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patricia Dubus Context triple: [Andre Dubus, spouse, Patricia Dubus]
-
A.
Peggy Dubus
chosen
Peggy Dubus is known as the former wife of American short story writer and essayist Andre Dubus.
-
B.
Patricia Dane
Patricia Dane was an American film actress of the 1940s who appeared in several MGM productions and was briefly married to bandleader Tommy Dorsey.
-
C.
Patricia Pearcy
Patricia Pearcy is an American actress best known for her roles in 1970s films and television, including notable appearances in cult and genre movies.
-
D.
Susan Patterson
Susan Patterson is an author and the wife and frequent collaborator of bestselling novelist James Patterson.
-
E.
Patricia Booker
Patricia Booker is an Australian former flight attendant best known as the first wife of media mogul Rupert Murdoch.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7613cec8190ac25e3f68c5d0edf |
completed | April 15, 2026, 12:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9dce8240819097efddb43b79ad4b |
completed | May 9, 2026, 2:37 a.m. |
Created at: April 10, 2026, 2:55 a.m.