Triple
T17409120
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Julia Arnold |
E423299
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Mary Augusta Ward |
—
|
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: Mary Augusta Ward | Statement: [Julia Arnold, relative, Mary Augusta Ward]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Augusta Ward Context triple: [Julia Arnold, relative, Mary Augusta Ward]
-
A.
Mary Augusta Ward
chosen
Mary Augusta Ward was a prominent late 19th- and early 20th-century British novelist and social reformer known for works such as "Robert Elsmere" and her influential role in Victorian intellectual life.
-
B.
Mary Jane Ward
Mary Jane Ward was an American novelist best known for her semi-autobiographical work "The Snake Pit," which exposed the harsh realities of mid-20th-century psychiatric institutions.
-
C.
Mary Lloyd
Mary Lloyd is a personal name shared by multiple individuals, including figures in fields such as the arts, military, and public life.
-
D.
Elizabeth Hodgkin
Elizabeth Hodgkin is the daughter of Nobel Prize–winning chemist and crystallographer Dorothy Hodgkin.
-
E.
Elizabeth Inglis
Elizabeth Inglis was a British actress best known for her roles in classic films such as "The Letter" and "The 39 Steps."
- 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_69d889d7d27c819088486ce3f0627fa1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43b0990f48190b62d73087ae1a0d7 |
completed | April 19, 2026, 2:16 a.m. |
Created at: April 10, 2026, 5:46 a.m.