Triple
T21763266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Max-3-SAT |
E537214
|
entity |
| Predicate | hasVariableDomain |
P64857
|
FINISHED |
| Object | Boolean variables |
—
|
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: Boolean variables | Statement: [Max-3-SAT, hasVariableDomain, Boolean variables]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVariableDomain Context triple: [Max-3-SAT, hasVariableDomain, Boolean variables]
-
A.
hasVariable
Indicates that one entity includes, defines, or is associated with a particular variable.
-
B.
domainOfVariables
chosen
Indicates that the predicate specifies the set or type of values that the variables involved in an expression or formula are allowed to take.
-
C.
hasVariableStatus
Indicates that an entity’s status is not fixed but can change over time or under different conditions.
-
D.
hasDependentVariable
Indicates that one variable’s value is determined by, or functionally depends on, the value(s) of another variable or set of variables.
-
E.
hasObservationDomain
Indicates that one entity is associated with, or belongs to, a specific observation domain within which its observations or measurements are grouped or managed.
- 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_69e0c46f5d1c8190bf830409e98464e5 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f031a711dc8190a786c9849dc344e8 |
completed | April 28, 2026, 4:03 a.m. |
| PD | Predicate disambiguation | batch_69e6be6299988190a34c98fa76d94700 |
completed | April 21, 2026, 12:01 a.m. |
Created at: April 16, 2026, 6:51 p.m.