Triple
T1138353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kähler manifold |
E23190
|
entity |
| Predicate | hasCohomologyProperty |
P23698
|
FINISHED |
| Object | admits Hodge decomposition |
—
|
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: admits Hodge decomposition | Statement: [Kähler manifold, hasCohomologyProperty, admits Hodge decomposition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCohomologyProperty Context triple: [Kähler manifold, hasCohomologyProperty, admits Hodge decomposition]
-
A.
isSimplyConnected
Indicates that a topological space has no "holes," meaning every loop within it can be continuously contracted to a single point.
-
B.
isHausdorff
Indicates that a topological space satisfies the Hausdorff separation property, meaning any two distinct points can be separated by disjoint open sets.
-
C.
haveProperty
chosen
Indicates that an entity possesses, exhibits, or is characterized by a particular property or attribute.
-
D.
isMaximallySymmetric
Indicates that the subject exhibits the highest possible degree of symmetry allowed by the relevant structure, constraints, or context.
-
E.
isHomogeneous
Indicates that all elements or parts involved share the same type, nature, or characteristics, without significant variation among them.
- 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_69a493ec75988190b63a11bafaec29b4 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bde18d208190848c189b2b8d585f |
completed | March 1, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69a4bb4b52d48190bec2e7ad1cc8efc0 |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:44 p.m.