Triple
T14907861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poniente |
E371181
|
entity |
| Predicate | airMassSource |
P116629
|
FINISHED |
| Object | maritime air mass from Atlantic |
—
|
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: maritime air mass from Atlantic | Statement: [Poniente, airMassSource, maritime air mass from Atlantic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airMassSource Context triple: [Poniente, airMassSource, maritime air mass from Atlantic]
-
A.
pollutionSource
Indicates that one entity is the origin or cause of pollution affecting another entity or environment.
-
B.
producesAerosol
Indicates that one entity generates or emits an aerosol (a suspension of fine solid particles or liquid droplets in air) as a result of its action or process.
-
C.
airSupplyMethod
Indicates the method or system by which air is provided or delivered to a space, device, or process.
-
D.
atmosphericEntry
Indicates the event of an object transitioning from space into a planetary atmosphere, experiencing aerodynamic forces and heating as it descends.
-
E.
targetPollutant
Indicates that something is the specific pollutant that is being aimed at, affected, or addressed by an action, process, or regulation.
- F. None of above. chosen
Provenance (4 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_69d85cc7ea3481908228b5acb7d06f12 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded61b3c808190b4f6df4e5cb401ad |
completed | April 15, 2026, 12:04 a.m. |
| PD | Predicate disambiguation | batch_69de9a4a14a88190951bb8f4c60bd37b |
completed | April 14, 2026, 7:49 p.m. |
| PDg | Predicate description generation | batch_69deb1a4d8dc8190a4c0841c20f2875f |
completed | April 14, 2026, 9:29 p.m. |
Created at: April 10, 2026, 2:23 a.m.