Triple
T10388780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Weil conjectures |
E244835
|
entity |
| Predicate | provedUsing |
P27215
|
FINISHED |
| Object | étale cohomology |
—
|
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: étale cohomology | Statement: [Weil conjectures, provedUsing, étale cohomology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: provedUsing Context triple: [Weil conjectures, provedUsing, étale cohomology]
-
A.
proved
Indicates that one entity has demonstrated the truth or validity of another entity (such as a statement, theorem, or claim) through logical or evidential means.
-
B.
provedUndecidableUsing
Indicates that the undecidability of one problem, theory, or statement was established by applying or reducing it to another specific method, result, or formal system.
-
C.
typicalProofUses
chosen
Indicates that a proof characteristically or commonly employs a particular method, technique, or component.
-
D.
partiallyProvenFor
Indicates that something has been shown to hold or be true for part of a domain or set of cases, but not yet for all cases.
-
E.
usedInProofStyle
Indicates that one entity is employed as a method, technique, or approach within the proof style or strategy of another entity.
- F. None of above.
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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9b40dd8819080ac839487020a44 |
completed | April 7, 2026, 11:25 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb0e7a88190bec0b7a52c70dfe2 |
completed | April 7, 2026, 10:42 a.m. |
Created at: April 6, 2026, 12:05 p.m.