Triple
T5256291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carathéodory’s theorem in convex geometry |
E118706
|
entity |
| Predicate | upperBound |
P14327
|
FINISHED |
| Object | n+1 points in ℝⁿ |
—
|
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: n+1 points in ℝⁿ | Statement: [Carathéodory’s theorem in convex geometry, upperBound, n+1 points in ℝⁿ]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upperBound Context triple: [Carathéodory’s theorem in convex geometry, upperBound, n+1 points in ℝⁿ]
-
A.
upperLimit
Indicates that one entity specifies the maximum allowable value, quantity, or boundary for another entity or condition.
-
B.
isUpperBoundFor
chosen
Indicates that one value is greater than or equal to every element in a given set or collection, serving as an upper limit for them.
-
C.
upperBandWidth
Indicates the maximum bandwidth limit or upper threshold of data transfer capacity allowed or supported in a given context.
-
D.
above
Indicates that one entity is positioned higher than another along a vertical axis, without implying direct contact.
-
E.
lowerLimit
Indicates that one value serves as the minimum or smallest allowable bound or threshold for another value or range.
- 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_69bd446978108190bb5f9c5c23d93f88 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7ba4ecd88190800b5e4eea3abed5 |
completed | March 20, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69bd77c30bac8190a883ca45da35d667 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:50 p.m.