Triple
T19541497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marie Jaworski |
E488914
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Marie Jaworski |
—
|
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: Marie Jaworski | Statement: [Marie Jaworski, name, Marie Jaworski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marie Jaworski Context triple: [Marie Jaworski, name, Marie Jaworski]
-
A.
Marie Jaworski
chosen
Marie Jaworski was the mother of Leon Jaworski, the prominent American lawyer best known as the Watergate special prosecutor.
-
B.
Marie Krackowizer
Marie Krackowizer was the wife of pioneering anthropologist Franz Boas and a supportive partner in his academic and intellectual life.
-
C.
Josephine Poszywak
Josephine Poszywak was the wife of American labor leader and Teamsters president Jimmy Hoffa.
-
D.
Judith Beneski
Judith Beneski is a notable member of the Beneski family, recognized for her significance within that family lineage.
-
E.
Jeanne Biegger
Jeanne Biegger was an American model and socialite best known as the second wife of entertainer Dean Martin, with whom she shared a highly publicized mid-20th-century Hollywood marriage.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63872fda48190bbb1f465cb7b57fe |
completed | April 20, 2026, 2:30 p.m. |
Created at: April 10, 2026, 1:41 p.m.