Triple
T21268263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hadley circulation |
E524186
|
entity |
| Predicate | surfaceBranchLocation |
P124124
|
FINISHED |
| Object | trade wind belt |
—
|
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: trade wind belt | Statement: [Hadley circulation, surfaceBranchLocation, trade wind belt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surfaceBranchLocation Context triple: [Hadley circulation, surfaceBranchLocation, trade wind belt]
-
A.
surfaceFeatureOf
Indicates that one entity is a surface-level characteristic, pattern, or feature belonging to or present on another entity.
-
B.
branchPoint
Indicates a point in a process, structure, or path where a single preceding element splits into two or more alternative continuations or options.
-
C.
branchPosition
Indicates the relative location or placement of something along a branch.
-
D.
structureOnSurface
Indicates that one entity is a structure physically situated on the surface of another entity.
-
E.
segmentLocation
chosen
Indicates the spatial or positional relationship specifying where a particular segment is located within a larger structure or context.
- 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_69e0b5156d7881909bd4f83676590715 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e735ee38cc81909b4e7c5996bb64f9 |
completed | April 21, 2026, 8:31 a.m. |
| PD | Predicate disambiguation | batch_69e5f6161dac8190b06009cd180e3ff7 |
completed | April 20, 2026, 9:47 a.m. |
Created at: April 16, 2026, 4 p.m.