Triple
T23634094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sapphire |
E583692
|
entity |
| Predicate | hasOpticalUse |
P7239
|
FINISHED |
| Object | infrared optics |
—
|
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: infrared optics | Statement: [Sapphire, hasOpticalUse, infrared optics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOpticalUse Context triple: [Sapphire, hasOpticalUse, infrared optics]
-
A.
hasOpticalElement
Indicates that one entity includes, contains, or is equipped with a specific optical element as a component or part.
-
B.
usesOpticsType
chosen
Indicates that one entity employs or is characterized by a specific type of optical system or technology.
-
C.
hasOpticalChannels
Indicates that an entity possesses one or more optical communication or signal-transmission channels.
-
D.
opticalSize
Indicates that one entity has a particular visual or perceived size relative to another, often dependent on viewing conditions or context.
-
E.
hasOpticalImageStabilization
Indicates that a device or component includes a feature that reduces image blur caused by camera movement during capture.
- 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_69e248fe1c2c8190ac914d2442ff3d26 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b1eb38a481909f7ceeaefb7b43ce |
completed | April 29, 2026, 7:23 a.m. |
| PD | Predicate disambiguation | batch_69f118d0e0588190a86527a7747c5427 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:47 p.m.