Triple
T17130956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Microwave Radiometer |
E415718
|
entity |
| Predicate | penetrationDepth |
P3822
|
FINISHED |
| Object | tens to hundreds of bars of pressure |
—
|
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: tens to hundreds of bars of pressure | Statement: [Microwave Radiometer, penetrationDepth, tens to hundreds of bars of pressure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: penetrationDepth Context triple: [Microwave Radiometer, penetrationDepth, tens to hundreds of bars of pressure]
-
A.
depthOrigin
Indicates the reference point or source location from which the depth of an object or region is measured.
-
B.
depth
chosen
Indicates the vertical distance from a reference surface or top point down to a lower point or bottom within a medium or space.
-
C.
designedTargetDepthInKilometers
Indicates the intended or planned depth, measured in kilometers, that something is designed to reach or operate at.
-
D.
bowDepth
Indicates the degree or extent to which one entity bows in relation to another.
-
E.
testDepth
Indicates that an entity is evaluated or measured based on how deep or thorough it is, often in terms of levels, layers, or extent below a surface or baseline.
- 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f029d1a48190a9d4094827d11d23 |
completed | April 18, 2026, 8:57 p.m. |
| PD | Predicate disambiguation | batch_69e3830192ac819091344a9e5a36c8c9 |
completed | April 18, 2026, 1:11 p.m. |
Created at: April 10, 2026, 5:36 a.m.