Triple
T19467214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | t-J model |
E487030
|
entity |
| Predicate | symbol_J_represents |
P121608
|
FINISHED |
| Object | antiferromagnetic exchange interaction |
—
|
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: antiferromagnetic exchange interaction | Statement: [t-J model, symbol_J_represents, antiferromagnetic exchange interaction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: symbol_J_represents Context triple: [t-J model, symbol_J_represents, antiferromagnetic exchange interaction]
-
A.
symbolNumber
Indicates a relationship where a specific numerical identifier is assigned to or associated with a particular symbol.
-
B.
symbolElement
Indicates that one entity is a constituent element or component that makes up the other entity, which is treated as a symbol.
-
C.
symbolIs
chosen
Indicates that one entity serves as the symbolic representation or sign of another entity.
-
D.
symbolizedIn
Indicates that one entity serves as a symbol or representation of another entity.
-
E.
symbolDerivation
Indicates a relationship where one symbol is derived, obtained, or formed from another symbol through some transformation or generative process.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633e2aee081908330a5665fa60482 |
completed | April 20, 2026, 2:10 p.m. |
| PD | Predicate disambiguation | batch_69e4fd7499a4819082bec0be8afba35c |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 1:39 p.m.