Triple
T23933527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Klebanov–Tseytlin background |
E602565
|
entity |
| Predicate | internalGeometry |
P25627
|
FINISHED |
| Object | conifold |
—
|
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: conifold | Statement: [Klebanov–Tseytlin background, internalGeometry, conifold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: internalGeometry Context triple: [Klebanov–Tseytlin background, internalGeometry, conifold]
-
A.
storesGeometryIn
Indicates that one entity holds or contains the geometric representation or spatial data of another entity.
-
B.
hasGeometry
chosen
Indicates that an entity is associated with a specific geometric representation or spatial form.
-
C.
viewGeometry
Indicates a relationship where a particular viewpoint or camera setup defines how a scene’s geometry is projected, framed, or visually represented.
-
D.
internalStructure
Indicates that one entity is a component, part, or substructure contained within the overall structure of another entity.
-
E.
testGeometry
Indicates that an entity is involved in evaluating, validating, or analyzing geometric properties, shapes, or spatial relationships.
- 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_69e2953cf6e081909b8e25a10a52dddc |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1cf9da9c4819085880c6ad521d7ed |
completed | April 29, 2026, 9:30 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:59 p.m.