Triple
T18344083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Olaf Stapledon |
E439487
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Agnes Zena Miller |
—
|
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: Agnes Zena Miller | Statement: [Olaf Stapledon, spouse, Agnes Zena Miller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Agnes Zena Miller Context triple: [Olaf Stapledon, spouse, Agnes Zena Miller]
-
A.
Agnes Zena Miller
chosen
Agnes Zena Miller was the wife of British philosopher and science fiction writer Olaf Stapledon.
-
B.
Agnes Smith
Agnes Smith is the daughter of Mrs. Anna Smith.
-
C.
Agnes Moore
Agnes Moore was the wife of acclaimed British actor Claude Rains, known primarily in relation to his personal life rather than for a prominent public career of her own.
-
D.
Agnes Marshall
Agnes Marshall was a pioneering 19th-century English cookery writer and entrepreneur, famed for her influential ice cream recipes and innovations in domestic cookery.
-
E.
Agnes Jervis
Agnes Jervis was the wife of English philosopher and literary critic George Henry Lewes, known primarily through her connection to his personal life.
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e514f2c8ec8190b045482846a68204 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 10:37 a.m.