Triple
T21922878
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | scanning tunneling microscope |
E541363
|
entity |
| Predicate | oftenOperatedIn |
P26656
|
FINISHED |
| Object | ultra-high vacuum |
—
|
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: ultra-high vacuum | Statement: [scanning tunneling microscope, oftenOperatedIn, ultra-high vacuum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenOperatedIn Context triple: [scanning tunneling microscope, oftenOperatedIn, ultra-high vacuum]
-
A.
oftenOperatedBy
Indicates that an entity is frequently or typically operated, controlled, or run by another entity.
-
B.
operatedAmong
Indicates that an entity carried out operations or activities within, or in coordination with, a specified group, set, or collection of other entities.
-
C.
operatedStationsIn
Indicates that an entity managed or ran the operations of one or more stations within a specified area or system.
-
D.
operatedNear
Indicates that one entity performed an operation or activity in close physical proximity to another entity.
-
E.
alsoOperatesIn
chosen
Indicates that an entity, in addition to its primary location or domain, conducts operations or activities in another specified place 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_69e0c47d74488190a15119108794a307 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1233d096c8190af0d7cd21879c91b |
completed | April 28, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:45 p.m.