Triple
T22019069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Syrkin |
E543789
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Marie Syrkin |
—
|
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: Marie Syrkin | Statement: [Syrkin, hasNotableBearer, Marie Syrkin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marie Syrkin Context triple: [Syrkin, hasNotableBearer, Marie Syrkin]
-
A.
Marie Syrkin
chosen
Marie Syrkin was an American Zionist intellectual, educator, and author known for her influential writings on Jewish identity, socialism, and the State of Israel.
-
B.
Rosa Stern
Rosa Stern was the maternal grandmother of Anne Frank and the mother of Edith Holländer, belonging to a German-Jewish family.
-
C.
Mildred Milstein
Mildred Milstein is a member of the prominent Milstein family, known for its significant business and philanthropic activities.
-
D.
Beatrice Levin
Beatrice Levin is a film producer known for her work on the legal drama thriller "The Mauritanian."
-
E.
Paula Jellinek
Paula Jellinek was a member of the Jellinek family, known for its close association with the early history of the Mercedes automobile brand.
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127c5929881908458d07bd33c5edd |
completed | April 28, 2026, 9:33 p.m. |
Created at: April 16, 2026, 8:23 p.m.