Triple
T23953783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yamabe problem |
E603721
|
entity |
| Predicate | furtherRefinedBy |
P112260
|
FINISHED |
| Object | Thierry Aubin |
—
|
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: Thierry Aubin | Statement: [Yamabe problem, furtherRefinedBy, Thierry Aubin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: furtherRefinedBy Context triple: [Yamabe problem, furtherRefinedBy, Thierry Aubin]
-
A.
refinementBy
chosen
Indicates that one entity serves as a more detailed, precise, or improved version of another entity.
-
B.
refinedIn
Indicates that one entity is processed or purified within a refining facility or operation to improve its quality or extract desired components.
-
C.
enhancedBy
Indicates that one entity’s value, effectiveness, or impact is increased or improved as a result of another entity.
-
D.
refinedConcept
Indicates that one concept is a more precise, detailed, or specialized version of another concept.
-
E.
hasRefinement
Indicates that one entity represents a more detailed, specific, or improved version 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_69e2954222288190a7323554d0cca8d7 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d0d558748190a51b5732a3e6713c |
completed | April 29, 2026, 9:35 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:21 p.m.