Triple
T3616213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DUNE experiment |
E76605
|
entity |
| Predicate | farDetectorDepth |
P9310
|
FINISHED |
| Object | approximately 1.5 kilometers underground |
—
|
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: approximately 1.5 kilometers underground | Statement: [DUNE experiment, farDetectorDepth, approximately 1.5 kilometers underground]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: farDetectorDepth Context triple: [DUNE experiment, farDetectorDepth, approximately 1.5 kilometers underground]
-
A.
depthClass
Indicates the categorical classification of an entity based on its depth or depth-related range.
-
B.
hasApproximateDepth
chosen
Indicates that an entity is associated with a depth value that is not exact but estimated or approximate.
-
C.
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.
-
D.
maxDepthLocation
Indicates the location at which the maximum depth of something (e.g., an object, structure, or feature) is reached or measured.
-
E.
depth
Indicates the vertical distance from a reference surface or top point down to a lower point or bottom within a medium or space.
- 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_69ad85dae2fc81908d1ceadbc6af0089 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc27c98088190a493c9eddf6b206a |
completed | March 8, 2026, 6:39 p.m. |
| PD | Predicate disambiguation | batch_69adb83f1e4c8190ab501c1c05b14c08 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:23 p.m.