Triple
T2437573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wolf Prize |
E53195
|
entity |
| Predicate | founder |
P104
|
FINISHED |
| Object | Ricardo Wolf |
E63105
|
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: Ricardo Wolf | Statement: [Wolf Prize, founder, Ricardo Wolf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ricardo Wolf Context triple: [Wolf Prize, founder, Ricardo Wolf]
-
A.
Ricardo Wolf
chosen
Ricardo Wolf was a German-born Cuban inventor, diplomat, and philanthropist best known for endowing the prestigious Wolf Prizes in fields such as mathematics and the arts and sciences.
-
B.
Felix Weil
Felix Weil was a German Marxist intellectual and wealthy benefactor best known for financing and helping to establish the Frankfurt School’s Institute for Social Research.
-
C.
Bruno Loerzer
Bruno Loerzer was a prominent German First World War fighter ace who later became a high-ranking Luftwaffe general during the Nazi era.
-
D.
Heiner Wilmer
Heiner Wilmer is a German Roman Catholic prelate who serves as the bishop of the Diocese of Hildesheim.
-
E.
Hugo Brunner
Hugo Brunner is a British public servant who served as the ceremonial representative of the monarch in Oxfordshire as its Lord Lieutenant.
- 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_69ab495b6dac8190ac82661aa1452222 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abc9f4d2dc8190b3c264a6c20d1bd5 |
completed | March 7, 2026, 6:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aef0ad31b8819084813b65b46bc9fc |
completed | March 9, 2026, 4:09 p.m. |
Created at: March 6, 2026, 9:43 p.m.