Triple
T5397577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ezra Pound |
E120693
|
entity |
| Predicate | partner |
P1136
|
FINISHED |
| Object | Olga Rudge |
E135288
|
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: Olga Rudge | Statement: [Ezra Pound, partner, Olga Rudge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olga Rudge Context triple: [Ezra Pound, partner, Olga Rudge]
-
A.
Olga Rudge
chosen
Olga Rudge was an American violinist and music scholar best known for her long-term relationship with poet Ezra Pound and her efforts to promote and preserve his work.
-
B.
Olga Kennard
Olga Kennard was a pioneering British crystallographer whose work in structural chemistry and data sharing led to the creation of the Cambridge Crystallographic Data Centre and significantly advanced the field of crystallography.
-
C.
Olga Peters
Olga Peters is the American-born daughter of Svetlana Alliluyeva, who was the only daughter of Soviet leader Joseph Stalin.
-
D.
Frances Rudge
Frances Rudge was the wife of influential American film and theatre director Elia Kazan.
-
E.
Eileen Soper
Eileen Soper was a British illustrator and etcher best known for her lively illustrations in Enid Blyton’s 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_69bd4637b92c8190b815b6443ae4b323 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd87485d5c819096ae574b1badc9d5 |
completed | March 20, 2026, 5:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf3379aae881909217c29aee856e5d |
completed | March 22, 2026, 12:10 a.m. |
Created at: March 20, 2026, 2:04 p.m.