Triple
T37946132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samsung Galaxy S7 |
E946609
|
entity |
| Predicate | frontProtection |
P103422
|
FINISHED |
| Object | Corning Gorilla Glass 4 |
—
|
NE NERFINISHED |
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: Corning Gorilla Glass 4 | Statement: [Samsung Galaxy S7, frontProtection, Corning Gorilla Glass 4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frontProtection Context triple: [Samsung Galaxy S7, frontProtection, Corning Gorilla Glass 4]
-
A.
frontMaterial
chosen
Indicates that one entity is the material that forms the front surface or front-facing part of another entity.
-
B.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
C.
frontAgainst
Indicates that one entity is positioned with its front side directly facing or pressed against the surface or side of another entity.
-
D.
front
Indicates that one entity is located directly before or facing another entity along a primary viewing or movement direction.
-
E.
frontPlacement
Indicates that one entity is positioned in front of another in space or sequence.
- 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_69f76ef531ac8190ae6d99e5786e76ec |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc995dc2481908b3bd4217f8101e7 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.