Triple
T995773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret Schlegel |
E21491
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Helen Schlegel |
E118206
|
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: Helen Schlegel | Statement: [Margaret Schlegel, sibling, Helen Schlegel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Helen Schlegel Context triple: [Margaret Schlegel, sibling, Helen Schlegel]
-
A.
Helen Schlegel
chosen
Helen Schlegel is an idealistic, impulsive young woman from E.M. Forster’s novel "Howards End," known for her passionate nature and progressive social views.
-
B.
Margaret Schlegel
Margaret Schlegel is the intelligent, idealistic, and culturally minded heroine of E.M. Forster’s novel "Howards End," who navigates issues of class, family, and social responsibility in Edwardian England.
-
C.
Helen Elliott
Helen Elliott was the wife of influential American psychologist Carl Rogers, supporting him throughout his career in developing client-centered therapy.
-
D.
Gwendolen
Gwendolen is the given name of Gwen Raverat, a notable British wood engraver and granddaughter of Charles Darwin.
-
E.
Dorothea
Dorothea is the middle name of Angela Merkel, the long-serving former chancellor of Germany.
- 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_69a493c476b48190b41fc5e793171cc6 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4df6dcc819084a7c0a50637a2c2 |
completed | March 1, 2026, 9:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac3ba52ebc819084e3d003a3ec8417 |
completed | March 7, 2026, 2:52 p.m. |
Created at: March 1, 2026, 7:41 p.m.