Triple
T14506451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Penrose spin networks |
E340275
|
entity |
| Predicate | edgeLabel |
P88300
|
FINISHED |
| Object | SU(2) spin representation |
—
|
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: SU(2) spin representation | Statement: [Penrose spin networks, edgeLabel, SU(2) spin representation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: edgeLabel Context triple: [Penrose spin networks, edgeLabel, SU(2) spin representation]
-
A.
edgeType
Indicates the specific kind or category of connection that exists between two related entities.
-
B.
namedOnEdge
chosen
Indicates that a name or label is assigned specifically to an edge (a connection or relationship) rather than to the nodes it links.
-
C.
typicalEdge
Indicates a standard or representative connection between two entities, as opposed to a special or exceptional type of edge.
-
D.
formsEdgeOf
Indicates that one entity constitutes a boundary or outer limit of another entity.
-
E.
edgeTreatment
Indicates a relationship where a specific method or process is applied to modify, finish, or protect the edge of an object or material.
- 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_69d822d9c0408190b9a2b3643e58bb4d |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69de94e25a2481908b8394e9a19f3b64 |
completed | April 14, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69de5c4ccba08190a988bfda0bc9f5cb |
completed | April 14, 2026, 3:25 p.m. |
Created at: April 10, 2026, 1:21 a.m.