Triple
T18391672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Corning Gorilla Glass 5 |
E449743
|
entity |
| Predicate | strengtheningMethod |
P118800
|
FINISHED |
| Object | chemical tempering |
—
|
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: chemical tempering | Statement: [Corning Gorilla Glass 5, strengtheningMethod, chemical tempering]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: strengtheningMethod Context triple: [Corning Gorilla Glass 5, strengtheningMethod, chemical tempering]
-
A.
strengtheningProcess
chosen
Indicates a process or set of actions that increases the strength, durability, or effectiveness of something over time.
-
B.
strengthensFrom
Indicates that one entity becomes stronger, more effective, or more intense as a result of influence, support, or input from another entity.
-
C.
strengthens
Indicates that one entity increases the power, effectiveness, or resilience of another.
-
D.
strengthenedStatusOf
Indicates that the status, condition, or standing of one entity has been made stronger or more robust in relation to another entity or context.
-
E.
reinforcedIn
Indicates that one entity is strengthened, supported, or made more robust within, or as a result of conditions in, another entity or context.
- 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_69d8b9fab8a8819086a9ddc0871715e0 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e518435cf481908393c1eb2b4ba659 |
completed | April 19, 2026, 6 p.m. |
| PD | Predicate disambiguation | batch_69e44ff1f92c8190afbb8e85d12bf2a9 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:46 a.m.