Triple
T6396940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bohr magneton |
E143963
|
entity |
| Predicate | usedAsUnitFor |
P12631
|
FINISHED |
| Object | magnetic moments of atoms |
—
|
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: magnetic moments of atoms | Statement: [Bohr magneton, usedAsUnitFor, magnetic moments of atoms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsUnitFor Context triple: [Bohr magneton, usedAsUnitFor, magnetic moments of atoms]
-
A.
basedUnit
Indicates that one unit is defined in terms of, or derived from, another more fundamental unit.
-
B.
unitOfMeasure
chosen
Indicates that one entity specifies the standard unit in which the quantity or value of another entity is measured.
-
C.
hasUnitOf
Indicates that a quantity, measurement, or value is expressed in terms of a specific unit.
-
D.
natureOfUnit
Indicates the type or category that characterizes what kind of unit something is (e.g., its nature or classification as a unit).
-
E.
basedUnitsInclude
Indicates that a composite or derived unit is defined using, and therefore includes, the specified base unit(s) in its construction.
- 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_69c008db906c819096f3597d55d95432 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c068953968819083a94f5de3e11819 |
completed | March 22, 2026, 10:09 p.m. |
| PD | Predicate disambiguation | batch_69c060f25c088190b433f78553ff1d84 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:35 p.m.