Triple
T30653424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Middle America Trench subduction interface |
E780320
|
entity |
| Predicate | seismogenicZoneDepth |
P114643
|
FINISHED |
| Object | to ~40–60 km |
—
|
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: to ~40–60 km | Statement: [Middle America Trench subduction interface, seismogenicZoneDepth, to ~40–60 km]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seismogenicZoneDepth Context triple: [Middle America Trench subduction interface, seismogenicZoneDepth, to ~40–60 km]
-
A.
subductionZoneDip
Indicates the angle at which one tectonic plate descends beneath another along a subduction zone.
-
B.
subductionRate
Indicates the rate at which one tectonic plate moves beneath another into the mantle along a subduction zone.
-
C.
typicalFocalDepthRange
chosen
Indicates the usual range of depths at which an event or phenomenon (such as an earthquake) most commonly occurs below the surface.
-
D.
maximumDepthKilometres
Indicates the greatest depth, measured in kilometers, that something reaches or extends to.
-
E.
affectsSubductionZone
Indicates that one entity has an influence or impact on the behavior, characteristics, or dynamics of a subduction zone.
- 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_69f224a5d2b481908a6853cd0138e2d7 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68a9a4d9081909d67b4dc73642cae |
completed | May 2, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69f6861170d08190bb98be609d436f84 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:30 p.m.