Triple
T12841105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rudolph Giuliani |
E307052
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Donna Hanover |
E307054
|
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: Donna Hanover | Statement: [Rudolph Giuliani, spouse, Donna Hanover]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donna Hanover Context triple: [Rudolph Giuliani, spouse, Donna Hanover]
-
A.
Donna Hanover
chosen
Donna Hanover is an American journalist, actress, and former First Lady of New York City, best known for her marriage to former New York City Mayor Rudy Giuliani.
-
B.
Barbara Havelone
Barbara Havelone is best known as the wife of American actor Lee Van Cleef, a prominent figure in classic Western films.
-
C.
Dolly Haas
Dolly Haas was a German-born actress and singer known for her work in European cinema and later on Broadway and in American films.
-
D.
Mollie Falk
Mollie Falk is a film and television producer best known for her work on the faith-based drama series "The Chosen."
-
E.
Daisy Werthan
Daisy Werthan is an elderly, sharp-tongued Jewish widow from Atlanta whose evolving relationship with her Black chauffeur forms the emotional core of the play and film "Driving Miss Daisy."
- 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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96ff2ab60819085561a3120189985 |
completed | April 10, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68edeaa1881909e06600ef88727de |
completed | May 2, 2026, 11:55 p.m. |
Created at: April 9, 2026, 5:35 p.m.