Triple
T9431002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aquamarine |
E227373
|
entity |
| Predicate | belongsToMineralSubclass |
P34461
|
FINISHED |
| Object | cyclosilicates |
—
|
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: cyclosilicates | Statement: [Aquamarine, belongsToMineralSubclass, cyclosilicates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToMineralSubclass Context triple: [Aquamarine, belongsToMineralSubclass, cyclosilicates]
-
A.
mineralGroup
chosen
Indicates that one entity is classified as a member or subtype of a particular mineral group defined by shared mineralogical characteristics.
-
B.
hasMineral
Indicates that one entity contains, includes, or is composed of a specified mineral.
-
C.
subclassOf
Indicates that one class is a more specific type of another class, inheriting its characteristics as a subset of it.
-
D.
belongsToSubfamily
Indicates that one entity is a member of, or classified within, a specific subfamily of another entity.
-
E.
isSubstrateOf
Indicates that one entity serves as the material or reactant upon which another entity (typically an enzyme or process) acts in a chemical or biochemical reaction.
- 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_69ca8437a7ac81908651de48f2d2141d |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd7e5ed7408190beda5fb078e9345a |
completed | April 1, 2026, 8:21 p.m. |
| PD | Predicate disambiguation | batch_69cca55548488190b171ae695a3212de |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:49 p.m.