Triple
T1249083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snell’s law of refraction |
E26832
|
entity |
| Predicate | angleMeasuredFrom |
P7801
|
FINISHED |
| Object | normal to the interface |
—
|
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: normal to the interface | Statement: [Snell’s law of refraction, angleMeasuredFrom, normal to the interface]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: angleMeasuredFrom Context triple: [Snell’s law of refraction, angleMeasuredFrom, normal to the interface]
-
A.
measuredFrom
chosen
Indicates that a measurement or value is determined relative to, or using, a specified reference point or source.
-
B.
measuredBy
Indicates that something’s quantity, extent, or value is determined or expressed using a particular measurement method, instrument, or unit.
-
C.
orientation
Indicates the relative directional alignment or facing of one entity with respect to another or to a reference frame.
-
D.
angularSize
Indicates the apparent size of an object as seen from a given point, typically measured as the angle it subtends at the observer.
-
E.
bendAngle
Indicates the degree to which one part is bent relative to another, typically measured as the angle formed at their joint or intersection.
- 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_69a49487a9c48190ba9b05348fd1b53f |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4bf83b32c81908648e5748b897247 |
completed | March 1, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69a4bb6b075881908e867c25b5080e25 |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:47 p.m.