Triple
T18952501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beauty (installation) |
E463687
|
entity |
| Predicate | employsScientificPrinciple |
P1757
|
FINISHED |
| Object | refraction of light |
—
|
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: refraction of light | Statement: [Beauty (installation), employsScientificPrinciple, refraction of light]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employsScientificPrinciple Context triple: [Beauty (installation), employsScientificPrinciple, refraction of light]
-
A.
usesPrinciple
chosen
Indicates that one entity applies, relies on, or is based upon a particular principle in its functioning, reasoning, or design.
-
B.
workingPrinciple
Indicates the fundamental mechanism or rule by which something operates or functions.
-
C.
implementsPrinciple
Indicates that an entity applies, follows, or puts into practice a specified principle in its design, behavior, or operation.
-
D.
isScientific
Indicates that something pertains to or is based on systematic scientific methods, principles, or knowledge.
-
E.
usesScientificMetaphor
Indicates that one entity employs scientific concepts or terminology metaphorically to describe or explain another entity or situation.
- 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d544fef8819091147189ddd89617 |
completed | April 20, 2026, 7:27 a.m. |
| PD | Predicate disambiguation | batch_69e4a2efec5c8190840704016bf547a1 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, noon