Triple
T12605183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sidney Lumet |
E300958
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mary Gimbel |
E300958
|
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: Mary Gimbel | Statement: [Sidney Lumet, spouse, Mary Gimbel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Gimbel Context triple: [Sidney Lumet, spouse, Mary Gimbel]
-
A.
Mary Gimbel
chosen
Mary Gimbel is best known as the first wife of acclaimed American film director Sidney Lumet.
-
B.
Helen Woolworth
Helen Woolworth was a member of the Woolworth family, known for its association with the influential American retail magnate F. W. Woolworth and his five-and-dime store empire.
-
C.
Edna Woolworth
Edna Woolworth was a daughter of American five-and-dime retail magnate Frank Winfield Woolworth and a member of the prominent Woolworth family.
-
D.
Lillian Goldman
Lillian Goldman was a philanthropist and major benefactor of legal education and libraries, notably supporting Yale Law School.
-
E.
Mary Boott
Mary Boott was the wife of American author and publisher Samuel Griswold Goodrich, known for his popular "Peter Parley" children's books.
- 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_69d7bdea2ca881908f379526c13b1145 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954e7f2dc8190a42cab7a0e5ea7f3 |
completed | April 10, 2026, 7:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65ecd1b748190bd961497b30e1ae5 |
completed | May 2, 2026, 8:30 p.m. |
Created at: April 9, 2026, 5:10 p.m.