Triple
T7406753
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | law of conservation of mass |
E170889
|
entity |
| Predicate | approximateFormOf |
P4460
|
FINISHED |
| Object | mass–energy conservation |
—
|
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: mass–energy conservation | Statement: [law of conservation of mass, approximateFormOf, mass–energy conservation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateFormOf Context triple: [law of conservation of mass, approximateFormOf, mass–energy conservation]
-
A.
approximates
chosen
Indicates that one entity is close to, but not exactly equal to, the value, form, or behavior of another entity.
-
B.
approximationType
Indicates the specific method or scheme used to approximate a value, function, or relationship in a given context.
-
C.
alternativeForm
Indicates that one entity is an alternative version, variant, or representation of another entity.
-
D.
isRealFormOf
Indicates that one entity is the actual, physically existing or fully realized version of another entity, which may be abstract, conceptual, or a representation.
-
E.
generalizedForm
Indicates that one entity is a more abstract, generalized version or broader form of another entity.
- 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_69c68a6010108190925e5284de022660 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f275c6e481908b4ce9ff1e418296 |
completed | March 27, 2026, 9:11 p.m. |
| PD | Predicate disambiguation | batch_69c6f0323b2c819098ab72c33e6d8534 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:10 p.m.