Triple
T19326542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barbier et Fenestre |
E483369
|
entity |
| Predicate | typeOfLensProduced |
P55795
|
FINISHED |
| Object | first-order Fresnel lenses |
—
|
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: first-order Fresnel lenses | Statement: [Barbier et Fenestre, typeOfLensProduced, first-order Fresnel lenses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfLensProduced Context triple: [Barbier et Fenestre, typeOfLensProduced, first-order Fresnel lenses]
-
A.
lensType
chosen
Indicates the specific kind or category of lens associated with or used by an entity.
-
B.
laterLensType
Indicates that one lens type occurs or is used at a later time than another lens type in a temporal sequence.
-
C.
lensManufacturer
Indicates that one entity is the company or maker responsible for producing the lens associated with another entity.
-
D.
usesLensBrand
Indicates that one entity employs or operates using a lens produced by a specific brand.
-
E.
usesLensMount
Indicates that one device or component is designed to accept, attach to, or operate with a specific type of lens mount.
- 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_69d8e8d13e3c81909d91d1d5ec37c095 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e6163e3a5081909195192356bcebc3 |
completed | April 20, 2026, 12:04 p.m. |
| PD | Predicate disambiguation | batch_69e4dd0ef66881909d489d634eee817a |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:33 p.m.