Triple
T19004802
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mississippi Embayment |
E465050
|
entity |
| Predicate | surfaceTopography |
P1242
|
FINISHED |
| Object | broad low-lying plain |
—
|
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: broad low-lying plain | Statement: [Mississippi Embayment, surfaceTopography, broad low-lying plain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surfaceTopography Context triple: [Mississippi Embayment, surfaceTopography, broad low-lying plain]
-
A.
surfaceFeatureOf
Indicates that one entity is a surface-level characteristic, pattern, or feature belonging to or present on another entity.
-
B.
surfaceType
chosen
Indicates the kind or classification of surface associated with an entity or interaction.
-
C.
surfaceDescription
Indicates that one entity provides a textual or qualitative description of the surface characteristics or appearance of another entity.
-
D.
topographyBasedOn
Indicates that the topographical characteristics of one entity are derived from, determined by, or modeled using the topography of another entity.
-
E.
referenceSurface
Indicates that one entity serves as the surface or base relative to which another entity is positioned, aligned, or defined.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6a3db9c8190a1bf0228e360a6e0 |
completed | April 20, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f88e0c81908cb20f08bf24cd32 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 12:01 p.m.