Triple
T22328724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kähler cone |
E551967
|
entity |
| Predicate | nonEmptyIf |
P67472
|
FINISHED |
| Object | manifold is Kähler |
—
|
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: manifold is Kähler | Statement: [Kähler cone, nonEmptyIf, manifold is Kähler]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nonEmptyIf Context triple: [Kähler cone, nonEmptyIf, manifold is Kähler]
-
A.
canBeEmpty
Indicates that something is allowed or able to have no content, elements, or value.
-
B.
isNonzeroFor
Indicates that a given value, function, or quantity is not equal to zero under specified conditions or for specified inputs.
-
C.
existsIf
chosen
Indicates that the existence or validity of one entity or condition depends on the presence or truth of another specified condition.
-
D.
isNonZeroBecause
Indicates that a value is non-zero specifically due to the stated cause, reason, or contributing factor.
-
E.
isNoncompact
Indicates that the object (such as a space or set) lacks compactness, meaning it does not satisfy the property that every open cover has a finite subcover.
- 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_69e11e482f788190b78d1588fc26d606 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15769fdb48190b84e0c019ab63579 |
completed | April 29, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69e73004d9e88190bb862319a5aea06b |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:43 p.m.