Triple
T6293585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernoulli numbers |
E141076
|
entity |
| Predicate | B_12 |
P70740
|
FINISHED |
| Object | -691/2730 |
—
|
LITERAL 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: -691/2730 | Statement: [Bernoulli numbers, B_12, -691/2730]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: B_12 Context triple: [Bernoulli numbers, B_12, -691/2730]
-
A.
deficiencyAssociatedWith
Indicates an association where a lack or insufficiency of one entity is related to the occurrence, presence, or severity of another entity.
-
B.
positionOnVitaminC
Indicates the stance, opinion, or policy that one entity holds regarding vitamin C.
-
C.
hasBioavailability
Indicates that a substance has a specified degree or measure of bioavailability, i.e., the proportion that enters circulation and can have an active effect.
-
D.
by
Indicates that an action is performed, caused, or authored through the agency, means, or proximity of a specified entity.
-
E.
fortifiedWith
Indicates that something has been strengthened, enhanced, or reinforced by the addition of a specified substance, feature, or element.
- F. None of above. chosen
Provenance (4 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_69c008cdf2ac8190bb640c94478fb4ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c06438654481908c9833c5f0d61773 |
completed | March 22, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69c060df0d8881908215575862ef6831 |
completed | March 22, 2026, 9:36 p.m. |
| PDg | Predicate description generation | batch_69c06284848c8190a0151ff3e8682889 |
completed | March 22, 2026, 9:43 p.m. |
Created at: March 22, 2026, 4:27 p.m.