Triple
T12729015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Betsy Wollheim |
E304181
|
entity |
| Predicate | hasRelative |
P367
|
FINISHED |
| Object | Elsa J. Wollheim |
E1038665
|
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: Elsa J. Wollheim | Statement: [Betsy Wollheim, hasRelative, Elsa J. Wollheim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elsa J. Wollheim Context triple: [Betsy Wollheim, hasRelative, Elsa J. Wollheim]
-
A.
Elsa J. Wollheim
chosen
Elsa J. Wollheim is the daughter of American editor and publisher Betsy Wollheim.
-
B.
Luise Straus-Ernst
Luise Straus-Ernst was a German art historian, critic, and writer associated with the Dada and Surrealist movements, who later became a victim of the Holocaust.
-
C.
Eileen Schauder Winters
Eileen Schauder Winters was the longtime wife of American comedian and actor Jonathan Winters.
-
D.
Marianne Ehrlich
Marianne Ehrlich was the daughter of Nobel Prize–winning German physician and immunologist Paul Ehrlich.
-
E.
Agnes M. Herzberg
Agnes M. Herzberg is a Canadian statistician known for her contributions to the design of experiments and for her leadership in the international statistics community.
- 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_69d7bdf1426c8190a4402e1c4cdec33a |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d964172490819080cd022ff8290b6e |
completed | April 10, 2026, 8:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f75d7a9e6c81908ae78daace02e7ec |
completed | May 3, 2026, 2:36 p.m. |
Created at: April 9, 2026, 5:25 p.m.