Triple
T8144041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kepler–Poinsot polyhedra |
E190163
|
entity |
| Predicate | generalize |
P2372
|
FINISHED |
| Object | convex regular polyhedra |
—
|
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: convex regular polyhedra | Statement: [Kepler–Poinsot polyhedra, generalize, convex regular polyhedra]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: generalize Context triple: [Kepler–Poinsot polyhedra, generalize, convex regular polyhedra]
-
A.
generalizationTo
Indicates that one concept or entity is a more general, abstract, or encompassing version of another, capturing a broader category or superset relationship.
-
B.
generalizationOf
chosen
Indicates that one entity represents a broader, more general concept or category that subsumes or abstracts over another, more specific entity.
-
C.
generalizationProperty
Indicates that one property is a more general, overarching version of another property, capturing a broader or more abstract relationship.
-
D.
general
Indicates that one entity has a broad, non-specific, or overarching relationship or association with another entity.
-
E.
generalizedForm
Indicates that one entity is a more abstract, generalized version or broader form 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_69ca82bd9900819099477cdc2eb4244f |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4444bb248190beaaa2ce4b8f3eaa |
completed | March 31, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69cb369c0d0481908762c488d7f77e74 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:36 p.m.