Triple
T2373644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ising model |
E46143
|
entity |
| Predicate | partitionFunctionSymbol |
P12746
|
FINISHED |
| Object | Z |
—
|
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: Z | Statement: [Ising model, partitionFunctionSymbol, Z]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partitionFunctionSymbol Context triple: [Ising model, partitionFunctionSymbol, Z]
-
A.
hasPartitionFunction
chosen
Indicates that an entity is associated with a specific partition function that characterizes its statistical or thermodynamic behavior.
-
B.
symbolType
Indicates the classification or category of a symbol based on its role, form, or function within a given system.
-
C.
characterFunction
Indicates the role, purpose, or narrative function that a character serves within a story or context.
-
D.
divisionRenamedFrom
Indicates that a division currently known by one name was previously known by another specified name.
-
E.
partAType
Indicates that one entity specifies or denotes the type or category of a particular part (part A) in relation to another entity.
- 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abca4d89248190be7d712d5fa8382b |
completed | March 7, 2026, 6:48 a.m. |
| PD | Predicate disambiguation | batch_69abc59d82f08190b7c36982d1ae783d |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:56 p.m.