Triple
T21401039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hépar |
E527910
|
entity |
| Predicate | hasKeySellingPoint |
P140461
|
FINISHED |
| Object | very high magnesium level compared to many waters |
—
|
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: very high magnesium level compared to many waters | Statement: [Hépar, hasKeySellingPoint, very high magnesium level compared to many waters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeySellingPoint Context triple: [Hépar, hasKeySellingPoint, very high magnesium level compared to many waters]
-
A.
hasMarketingPoint
chosen
Indicates that an entity possesses or is associated with a specific marketing-related feature, advantage, or talking point.
-
B.
hasSalesComponent
Indicates that something includes, involves, or is associated with a sales-related element or function.
-
C.
hasKeyPoint
Indicates that one entity includes, contains, or is associated with a specific key point or main idea represented by another entity.
-
D.
hasKeyBusiness
Indicates that one entity possesses or is associated with a primary or strategically important business of another entity.
-
E.
hasMarketingElement
Indicates that one entity includes, is associated with, or makes use of a particular marketing-related component or feature.
- 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_69e0b520ee3c8190abddbee7e37e834c |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b16f7c5081909475eb5bb6177955 |
completed | April 22, 2026, 11:30 a.m. |
| PD | Predicate disambiguation | batch_69e61633f8208190a2a849457c4e4198 |
completed | April 20, 2026, 12:04 p.m. |
Created at: April 16, 2026, 5:15 p.m.