Triple
T18729780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neumann’s principle |
E458004
|
entity |
| Predicate | relatesSymmetryOf |
P120833
|
FINISHED |
| Object | physical properties |
—
|
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: physical properties | Statement: [Neumann’s principle, relatesSymmetryOf, physical properties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatesSymmetryOf Context triple: [Neumann’s principle, relatesSymmetryOf, physical properties]
-
A.
symmetryOf
Indicates that one entity is the symmetry counterpart or symmetric form of another entity, typically related by a specific symmetry operation or transformation.
-
B.
symmetryInvolved
chosen
Indicates that a relationship or action inherently involves symmetry, such as invariance under certain transformations or the presence of symmetric structure or behavior.
-
C.
testsSymmetry
Indicates that one entity evaluates or verifies whether a relationship or property holds identically in both directions between two entities.
-
D.
isSymmetricAbout
Indicates that one entity is a mirror image of another with respect to a specified axis, point, or plane of symmetry.
-
E.
localSymmetry
Indicates that an entity exhibits symmetry within a localized region or subset of its structure, rather than across its entire extent.
- 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_69d8d393ba9c8190a8b03b04ddbb0a09 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56d7660488190b4f70db963d05ef6 |
completed | April 20, 2026, 12:04 a.m. |
| PD | Predicate disambiguation | batch_69e48d03766c8190a43f7681842f4f8d |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:50 a.m.