Triple
T49087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rebecca Nurse |
E964
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Mary Easty |
E19336
|
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: Mary Easty | Statement: [Rebecca Nurse, sibling, Mary Easty]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Easty Context triple: [Rebecca Nurse, sibling, Mary Easty]
-
A.
Mary Easty
chosen
Mary Easty was a respected Salem, Massachusetts woman who was falsely accused of witchcraft and executed during the 1692 Salem witch trials, later remembered for her dignified plea for justice.
-
B.
Mary Louise Bell
Mary Louise Bell was the first wife of renowned physicist Richard Feynman, whom he married after the death of his childhood sweetheart Arline Greenbaum.
-
C.
Mary Lee Woods
Mary Lee Woods was a British mathematician and computer scientist who worked on early computers at Ferranti and was the mother of World Wide Web inventor Tim Berners-Lee.
-
D.
Jane Belson
Jane Belson was a British barrister best known as the wife of author Douglas Adams.
-
E.
Lucille Sheardown
Lucille Sheardown was one of the later wives of American inventor Lee de Forest, associated with his personal life rather than his pioneering work in radio and electronics.
- 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24af3e4a88190abe2f0c5a0e83ff3 |
completed | Feb. 28, 2026, 1:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3a5cd067c8190a25649f80c69ee89 |
completed | March 1, 2026, 2:34 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.