Triple
T1348268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Planck constant |
E28819
|
entity |
| Predicate | isInvariant |
P4235
|
FINISHED |
| Object | Lorentz invariant |
—
|
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: Lorentz invariant | Statement: [Planck constant, isInvariant, Lorentz invariant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isInvariant Context triple: [Planck constant, isInvariant, Lorentz invariant]
-
A.
invariantType
Indicates that one entity has a type or classification that remains constant or unchanged under specified conditions or transformations.
-
B.
invariantUnder
chosen
Indicates that a property, structure, or quantity remains unchanged when a specified transformation or operation is applied.
-
C.
invariantInterval
Indicates that a certain interval or range remains unchanged or constant under a specified transformation or set of conditions.
-
D.
hasCurvatureInvariant
Indicates that one entity possesses a specific curvature-related invariant property or value associated with its geometric or mathematical structure.
-
E.
isStable
Indicates that the state, condition, or configuration of an entity does not change significantly over time or under expected variations in its environment.
- 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_69a498571d248190a0ac9eb02d97097f |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c2418e38819094683d6e1efc6e56 |
completed | March 1, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69a4bef5857c81909ae984feb85a26ca |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:56 p.m.