Triple
T25433021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roth's theorem |
E637307
|
entity |
| Predicate | sharpens |
P3261
|
FINISHED |
| Object | Liouville's theorem on Diophantine approximation |
—
|
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: Liouville's theorem on Diophantine approximation | Statement: [Roth's theorem, sharpens, Liouville's theorem on Diophantine approximation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharpens Context triple: [Roth's theorem, sharpens, Liouville's theorem on Diophantine approximation]
-
A.
sharpeningType
Indicates the method or style by which something is sharpened or made sharper.
-
B.
sharpnessCondition
Indicates the condition or degree of sharpness that something possesses or is required to have.
-
C.
strengthens
chosen
Indicates that one entity increases the power, effectiveness, or resilience of another.
-
D.
sharpnessWitnessedBy
Indicates that the sharpness of an object or edge is observed, perceived, or recorded by a particular witness or observer.
-
E.
bladeEdge
Indicates that one entity is the cutting edge or sharpened boundary of a blade-related object in relation to 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_69e75db58a1c8190891b9ff7c2f8414e |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f6dc7d088190b1e4c191172ea256 |
completed | May 2, 2026, 1:06 p.m. |
| PD | Predicate disambiguation | batch_69f4683b34748190818428489a226124 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 1:58 p.m.