Triple
T3785650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs Beeton |
E85523
|
entity |
| Predicate | marriedName |
P18
|
FINISHED |
| Object | Isabella Mary Beeton |
E85523
|
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: Isabella Mary Beeton | Statement: [Mrs Beeton, marriedName, Isabella Mary Beeton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isabella Mary Beeton Context triple: [Mrs Beeton, marriedName, Isabella Mary Beeton]
-
A.
Mrs Beeton
chosen
Mrs Beeton was a 19th-century English writer best known for her hugely influential household management and cookery book, "Mrs Beeton's Book of Household Management."
-
B.
Eliza Smith
Eliza Smith was the wife of renowned British neoclassical architect Sir John Soane.
-
C.
Bessie Maddern London
Bessie Maddern London was an American stage actress and writer best known as the first wife of author Jack London.
-
D.
Elizabeth Fisher
Elizabeth Fisher was the wife of Mayflower passenger and Plymouth Colony leader Stephen Hopkins, known primarily through her connection to early colonial American history.
-
E.
Emma C. Berry
Emma C. Berry is a historic 19th-century fishing schooner preserved as one of the oldest surviving commercial vessels of her type in the United States.
- 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_69aed937fa8881908208ef3801060826 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee42d2bc88190ab85529fcd1aa20a |
completed | March 9, 2026, 3:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4fb1c90648190a76cee07508a83b9 |
completed | March 14, 2026, 6:07 a.m. |
Created at: March 9, 2026, 3:13 p.m.