Triple
T13658762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maras District |
E326927
|
entity |
| Predicate | hasSaltSource |
P84201
|
FINISHED |
| Object | subterranean saline spring |
—
|
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: subterranean saline spring | Statement: [Maras District, hasSaltSource, subterranean saline spring]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSaltSource Context triple: [Maras District, hasSaltSource, subterranean saline spring]
-
A.
saltSource
chosen
Indicates that one entity serves as the origin or provider of salt for another entity or process.
-
B.
saltingMethod
Indicates the technique or process used to apply salt to something, such as food or materials.
-
C.
hasSugarSource
Indicates that one entity serves as the source or provider of sugar for another entity.
-
D.
containsSaltDeposit
Indicates that one entity has or includes a salt deposit within its area, volume, or structure.
-
E.
hasSaltPans
Indicates that one entity possesses, contains, or is characterized by salt pans (areas where salt is naturally deposited or harvested).
- 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_69d8076d8270819092afc2f0e9c359a8 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc61f0d808190b1cd2a6ba0d930eb |
completed | April 12, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69dbbe8a027081908d8f884b89707a5e |
completed | April 12, 2026, 3:47 p.m. |
Created at: April 9, 2026, 9:52 p.m.