Triple
T18585992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Memorial |
E454236
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Alice Oswald |
—
|
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: Alice Oswald | Statement: [Memorial, author, Alice Oswald]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alice Oswald Context triple: [Memorial, author, Alice Oswald]
-
A.
Alice Oswald
chosen
Alice Oswald is a contemporary British poet renowned for her innovative, nature-focused verse and acclaimed works such as "Dart" and "Memorial."
-
B.
Elizabeth Nicholas
Elizabeth Nicholas was the wife of Edmund Randolph, an early American statesman who served as the first U.S. Attorney General and second Secretary of State.
-
C.
Grace Darmond
Grace Darmond was a Canadian-born silent film actress of the 1910s and 1920s, known for her roles in early Hollywood productions.
-
D.
Louise Doughty
Louise Doughty is a British novelist, playwright, and journalist best known for her psychological thrillers and critically acclaimed works of literary fiction.
-
E.
Prunella Gee
Prunella Gee is a British actress known for her film, television, and stage work, particularly in British productions of the 1970s and 1980s.
- 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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e545b210488190ba62d3bf6e1a595c |
completed | April 19, 2026, 9:14 p.m. |
Created at: April 10, 2026, 11:44 a.m.