Triple
T8445916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mediterranean Outflow Water |
E199675
|
entity |
| Predicate | spreadsAlong |
P73778
|
FINISHED |
| Object | isopycnal surfaces |
—
|
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: isopycnal surfaces | Statement: [Mediterranean Outflow Water, spreadsAlong, isopycnal surfaces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spreadsAlong Context triple: [Mediterranean Outflow Water, spreadsAlong, isopycnal surfaces]
-
A.
spreadsAs
chosen
Indicates that one entity propagates, extends, or disseminates from another entity or source.
-
B.
spreadBy
Indicates that something is transmitted, dispersed, or propagated through the agency or action of a specified entity or medium.
-
C.
spreadTo
Indicates that something extends, propagates, or is transmitted from one entity, location, or context to another.
-
D.
spreadingStyle
Indicates how an entity extends, disperses, or propagates from its source across a medium, area, or set of targets.
-
E.
expandedAcross
Indicates that something has grown or extended so that it now spans or covers multiple areas, regions, or segments.
- 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_69ca83170f9081909cd98f55614c6476 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe3152a3c819092efdeab718def7a |
completed | March 31, 2026, 3:07 p.m. |
| PD | Predicate disambiguation | batch_69cbd0f5a3648190beb53a139a2d5482 |
completed | March 31, 2026, 1:49 p.m. |
Created at: March 30, 2026, 6:09 p.m.