Triple
T30040990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NMOS |
E763300
|
entity |
| Predicate | fabricationIncludes |
P47069
|
FINISHED |
| Object | source and drain n+ diffusion regions |
—
|
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: source and drain n+ diffusion regions | Statement: [NMOS, fabricationIncludes, source and drain n+ diffusion regions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fabricationIncludes Context triple: [NMOS, fabricationIncludes, source and drain n+ diffusion regions]
-
A.
coFabricator
Indicates that two or more entities jointly fabricate, construct, or produce something together.
-
B.
fabricationTechnology
Indicates the manufacturing or production method used to create or realize an entity.
-
C.
partOfProduction
chosen
Indicates that one entity functions as a component, segment, or phase within the overall process or structure of another production.
-
D.
fabricatedOn
Indicates that something was manufactured, constructed, or produced at a specific time or date.
-
E.
madeWith
Indicates that one entity is created, produced, or constructed using another entity as a material, ingredient, or component.
- 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_69f2246fb2b88190acff36bf7975c8f0 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f679d8525881909915ac704ab1ac30 |
completed | May 2, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 6:53 p.m.