Triple
T29514235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graham's number |
E748745
|
entity |
| Predicate | muchLargerThan |
P10621
|
FINISHED |
| Object | best known lower bound for the corresponding Ramsey number |
—
|
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: best known lower bound for the corresponding Ramsey number | Statement: [Graham's number, muchLargerThan, best known lower bound for the corresponding Ramsey number]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: muchLargerThan Context triple: [Graham's number, muchLargerThan, best known lower bound for the corresponding Ramsey number]
-
A.
largerThan
chosen
Indicates that one entity has a greater size, extent, or magnitude than another entity.
-
B.
isHeavierThan
Indicates that one entity has greater weight or mass than another entity.
-
C.
moreExpensiveThan
Indicates that one entity has a higher cost or price than another entity.
-
D.
isLargestOf
Indicates that one entity has the greatest size, extent, or magnitude among a specified set of entities.
-
E.
offersMoreSpaceThan
Indicates that one entity provides a greater amount of space or capacity than 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_69f0bd461c208190bec20bbf24e02cc5 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66c61be488190b4a8f39c94a76409 |
completed | May 2, 2026, 9:28 p.m. |
| PD | Predicate disambiguation | batch_69f6633ac8a88190ab0cda62bbfcf9b0 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 4:35 p.m.