Triple
T16125266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susanna Nelson |
E391251
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Ann Nelson |
—
|
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: Ann Nelson | Statement: [Susanna Nelson, sibling, Ann Nelson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ann Nelson Context triple: [Susanna Nelson, sibling, Ann Nelson]
-
A.
Ann Nelson
chosen
Ann Nelson is the daughter of Edmund Nelson, a British clergyman best known as the father of Admiral Horatio Nelson.
-
B.
Ann Nelson
Ann Nelson was an influential American theoretical physicist known for her work on particle physics, including theories of electroweak symmetry breaking, CP violation, and dark matter.
-
C.
Ann Nelson
Ann Nelson was an American character actress best known for her recurring role as the elderly diner patron Mrs. Gertrude Berg on the television series "Fame" and numerous film and TV appearances.
-
D.
Nancy Dow
Nancy Dow was an American actress and model best known as the mother of Jennifer Aniston.
-
E.
Nancy Deale
Nancy Deale was an American actress and the wife of Canadian actor Lorne Greene, known for her work in film and television during the mid-20th century.
- 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_69d87f1bb0988190b490d273dbf3fd03 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2020408a88190bf3dfc893d577c55 |
completed | April 17, 2026, 9:48 a.m. |
Created at: April 10, 2026, 5 a.m.