Triple
T20780103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlantic Water |
E511454
|
entity |
| Predicate | typicalSalinityRange |
P1181
|
FINISHED |
| Object | 34.8–35.2 psu (approximate) |
—
|
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: 34.8–35.2 psu (approximate) | Statement: [Atlantic Water, typicalSalinityRange, 34.8–35.2 psu (approximate)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalSalinityRange Context triple: [Atlantic Water, typicalSalinityRange, 34.8–35.2 psu (approximate)]
-
A.
hasSalinityRange
chosen
Indicates the range of salinity values within which something (such as a substance, environment, or organism) is present, applicable, or able to function.
-
B.
salinityRegime
Indicates the pattern or level of salt concentration characterizing an environment or system over time.
-
C.
salinityPreference
Indicates the preferred range or level of salinity under which an entity most optimally exists, functions, or occurs.
-
D.
salinity
Indicates the concentration of dissolved salts present in or affecting something, typically a body of water or environment.
-
E.
hasSalinityType
Indicates the type or category of salinity associated with an entity, such as its salinity level or classification.
- 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_69e0b4cac7a48190a715cb3d545df2b4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c26f99b88190a84a6889834e1e96 |
completed | April 21, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_69e5c0550ec481908a0877fb2409d983 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:37 p.m.