Triple
T15397609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epsom salts |
E368217
|
entity |
| Predicate | regulatesNutrient |
P118642
|
FINISHED |
| Object | magnesium levels in soil |
—
|
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: magnesium levels in soil | Statement: [Epsom salts, regulatesNutrient, magnesium levels in soil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regulatesNutrient Context triple: [Epsom salts, regulatesNutrient, magnesium levels in soil]
-
A.
nutritionMode
Indicates the way an entity obtains or processes nutrients for sustenance or growth.
-
B.
hasNutrientStatus
Indicates that an entity possesses a particular nutritional condition or level, such as being deficient, sufficient, or excessive in specific nutrients.
-
C.
nutritionType
Indicates the specific category or kind of nutritional characteristic or value associated with an entity.
-
D.
nutritionStandard
Indicates that something complies with, or is evaluated against, a defined set of nutritional guidelines or requirements.
-
E.
hasNutrientContent
Indicates that one entity contains or provides a specified amount or type of nutrient relative to another entity or standard.
- 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_69d85a16c68c819099c1b547fbc87b32 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e8c5d40819086622b70edcb6294 |
completed | April 16, 2026, 1:42 a.m. |
| PD | Predicate disambiguation | batch_69ded27b8cac8190bfa77698d53c5d1c |
completed | April 14, 2026, 11:49 p.m. |
| PDg | Predicate description generation | batch_69ded57005608190886cd01f640dfedb |
completed | April 15, 2026, 12:01 a.m. |
Created at: April 10, 2026, 3:19 a.m.