Triple
T38567837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gelfand–Tsetlin graph |
E928276
|
entity |
| Predicate | hasVertexSetDescription |
P77195
|
FINISHED |
| Object | vertices are Gelfand–Tsetlin patterns |
—
|
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: vertices are Gelfand–Tsetlin patterns | Statement: [Gelfand–Tsetlin graph, hasVertexSetDescription, vertices are Gelfand–Tsetlin patterns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVertexSetDescription Context triple: [Gelfand–Tsetlin graph, hasVertexSetDescription, vertices are Gelfand–Tsetlin patterns]
-
A.
hasVertexSet
chosen
Indicates that a graph or geometric object is associated with, or defined by, a specific set of vertices.
-
B.
hasVertex
Indicates that an object, typically a geometric shape or graph, includes a specified vertex as one of its corner or node points.
-
C.
hasVertexFigure
Indicates that one geometric figure has another specific figure as its vertex figure, describing the local shape around each vertex.
-
D.
hasCoordinateDescription
Indicates that an entity is associated with a textual or structured description of its spatial or geographic coordinates.
-
E.
hasNumberOfFeaturesDescribed
Indicates that an entity is associated with a specific count of its features that have been described.
- 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_69f76eb8d1808190a588af29d8b266d6 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.