Triple
T23801758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nirenberg problem |
E588691
|
entity |
| Predicate | manifoldType |
P152475
|
FINISHED |
| Object | sphere |
—
|
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: sphere | Statement: [Nirenberg problem, manifoldType, sphere]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: manifoldType Context triple: [Nirenberg problem, manifoldType, sphere]
-
A.
hasManifoldStructure
Indicates that one entity endows or possesses a manifold structure on or over another entity.
-
B.
dimensionType
Indicates the specific kind or category of dimension that characterizes how something is measured or structured.
-
C.
isSmoothManifold
chosen
Indicates that the entity is a manifold whose local structure is modeled on smooth Euclidean space and whose transition maps are infinitely differentiable.
-
D.
morphismType
Indicates the specific kind or category of morphism that characterizes the structural relationship between two mathematical objects.
-
E.
homotopyType
Indicates that two topological spaces or maps share the same homotopy type, meaning they can be continuously deformed into one another up to homotopy.
- 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_69e25d15db58819092ac1e6791696fd9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c74e430481909debd10c71785912 |
completed | April 29, 2026, 8:54 a.m. |
| PD | Predicate disambiguation | batch_69f155fe300481909bd617443228df65 |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:53 p.m.