Triple
T16249122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oskar Homolka |
E394450
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Florence Meyer |
—
|
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: Florence Meyer | Statement: [Oskar Homolka, spouse, Florence Meyer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Florence Meyer Context triple: [Oskar Homolka, spouse, Florence Meyer]
-
A.
Florence Meyer
chosen
Florence Meyer was an American portrait photographer and socialite known for her work in artistic and society circles in the mid-20th century.
-
B.
Florence Klotz
Florence Klotz was an American costume designer renowned for her Tony Award–winning work on Broadway musicals, particularly in collaboration with Stephen Sondheim.
-
C.
Florence Herman
Florence Herman was the wife of American modernist poet and physician William Carlos Williams.
-
D.
Florence Wyman Richardson
Florence Wyman Richardson was an American woman best known as the mother of Hadley Richardson, the first wife of writer Ernest Hemingway.
-
E.
Florence Williamson
Florence Williamson is a film editor known for her work on the 1972 musical historical comedy film "1776."
- 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_69d87f2171208190951025e526947816 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e24594f23c8190bd59fcb2585cb5e3 |
completed | April 17, 2026, 2:37 p.m. |
Created at: April 10, 2026, 5:04 a.m.