Triple
T7486718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VISIR |
E176898
|
entity |
| Predicate | typicalWavelengthCoverageMicrons |
P45250
|
FINISHED |
| Object | 8–25 micrometres |
—
|
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: 8–25 micrometres | Statement: [VISIR, typicalWavelengthCoverageMicrons, 8–25 micrometres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalWavelengthCoverageMicrons Context triple: [VISIR, typicalWavelengthCoverageMicrons, 8–25 micrometres]
-
A.
wavelengthRangeLowerBoundMicrometers
Indicates the minimum wavelength value, expressed in micrometers, that defines the lower limit of a wavelength range for the related entity or measurement.
-
B.
supportsWavelengthRange
chosen
Indicates that an entity is capable of operating over, handling, or being compatible with a specified range of wavelengths.
-
C.
hasObservationWavelength
Indicates the specific wavelength at which an observation or measurement is made or recorded.
-
D.
spectralResolution
Indicates the fineness with which a system can distinguish or separate different wavelengths or frequencies within a spectrum.
-
E.
emissivityRange
Indicates the range of emissivity values within which an entity’s emission-related property is valid or characterized.
- 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_69c69f24ac508190bb98fe927c0bd065 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5582adc81908b68439762965d88 |
completed | March 27, 2026, 9:23 p.m. |
| PD | Predicate disambiguation | batch_69c6f03eeaa88190a5215772ed05ee9f |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:42 p.m.