Triple
T18815845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | beryllium |
E460131
|
entity |
| Predicate | alloyWith |
P108185
|
FINISHED |
| Object | copper |
—
|
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: copper | Statement: [beryllium, alloyWith, copper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alloyWith Context triple: [beryllium, alloyWith, copper]
-
A.
formsAlloysWith
chosen
Indicates that two substances can combine to form a homogeneous metallic alloy with each other.
-
B.
commonAlloyName
Indicates that one entity is the commonly used or recognized alloy name corresponding to another entity representing that alloy.
-
C.
alsoComposedWith
Indicates that something is created or formed together with one or more additional components, highlighting a joint or complementary composition relationship.
-
D.
associatedMetal
Indicates a relationship where one entity is linked or connected to a particular metal, such as by composition, usage, origin, or symbolic association.
-
E.
inlaidWith
Indicates that one object has decorative material set into its surface, typically flush with it, using a contrasting substance or pattern.
- 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_69d8d398c7d4819091cb2f7e48948aeb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5a3e092e081908fc310c70f646e79 |
completed | April 20, 2026, 3:56 a.m. |
| PD | Predicate disambiguation | batch_69e48d1b10ec8190985c6fb5766ff981 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:53 a.m.