Triple
T19260252
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clark Refractor |
E481627
|
entity |
| Predicate | hasMirrorOrLensMaterial |
P135091
|
FINISHED |
| Object | optical glass |
—
|
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: optical glass | Statement: [Clark Refractor, hasMirrorOrLensMaterial, optical glass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMirrorOrLensMaterial Context triple: [Clark Refractor, hasMirrorOrLensMaterial, optical glass]
-
A.
hasOpticalElement
Indicates that one entity includes, contains, or is equipped with a specific optical element as a component or part.
-
B.
hasLanternMaterial
Indicates that an entity’s lantern is made from or composed of a specified material.
-
C.
hasMaterialOption
Indicates that an entity can be made from, or is available in, one or more alternative materials.
-
D.
hasNanoTextureGlassOption
Indicates that an entity offers or includes an available option for nano-texture glass.
-
E.
isMaterialSpecific
Indicates that a relationship, rule, or property applies only to a particular material or set of materials, rather than being generally applicable.
- F. None of above. chosen
Provenance (4 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_69d8e8cd9d1081908a181d02b88b59b8 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fb890e7c8190beba407f63459382 |
completed | April 20, 2026, 10:10 a.m. |
| PD | Predicate disambiguation | batch_69e4dd002d00819088b625056edfb74e |
completed | April 19, 2026, 1:47 p.m. |
| PDg | Predicate description generation | batch_69e4ddcf50108190a09d0f1291c17374 |
completed | April 19, 2026, 1:51 p.m. |
Created at: April 10, 2026, 1:28 p.m.