Triple
T18206219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sidney Paget |
E435909
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Walter Paget |
—
|
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: Walter Paget | Statement: [Sidney Paget, sibling, Walter Paget]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Walter Paget Context triple: [Sidney Paget, sibling, Walter Paget]
-
A.
Walter Paget
chosen
Walter Paget was a British illustrator of the late 19th and early 20th centuries, known for his work on adventure and historical novels.
-
B.
Francis Paget
Francis Paget was an English theologian and Anglican bishop who served as Bishop of Oxford in the late 19th and early 20th centuries.
-
C.
Sir James Paget
Sir James Paget was a prominent 19th-century English surgeon and pathologist, renowned as one of the founders of modern pathology and for describing several medical conditions that bear his name.
-
D.
Alfred Paget
Alfred Paget was a British silent film actor known for his numerous roles in early 20th-century cinema, often appearing in D.W. Griffith productions.
-
E.
George Edward Paget
George Edward Paget was a 19th-century English physician and academic known for his contributions to clinical medicine and medical education at the University of Cambridge.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e2234b988190bbe2c2164d61f65f |
completed | April 19, 2026, 2:09 p.m. |
Created at: April 10, 2026, 10:32 a.m.