Triple
T29514233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graham's number |
E748745
|
entity |
| Predicate | roleInProof |
P63687
|
FINISHED |
| Object | upper bound on a specific 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: upper bound on a specific Ramsey number | Statement: [Graham's number, roleInProof, upper bound on a specific Ramsey number]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInProof Context triple: [Graham's number, roleInProof, upper bound on a specific Ramsey number]
-
A.
proofRole
chosen
Indicates the specific function or responsibility an entity has within the structure or presentation of a proof.
-
B.
roleInCollateral
Indicates that an entity participates in or is assigned a specific role within a collateral arrangement or structure.
-
C.
roleInText
Indicates that an entity participates in a text with a specific function or capacity (e.g., author, editor, character).
-
D.
representedRole
Indicates that one entity serves as a stand-in, proxy, or representative performing a role on behalf of another entity.
-
E.
roleInMetadata
Indicates that an entity serves a specific function or position within a metadata record or metadata structure.
- 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_69ff0d80c0dc81909fbd12285c7a45c0 |
completed | May 9, 2026, 10:33 a.m. |
| PD | Predicate disambiguation | batch_69ff0cd03e78819094895058f925fbfa |
completed | May 9, 2026, 10:30 a.m. |
Created at: April 28, 2026, 4:35 p.m.