Triple
T31819663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Polish notation |
E812224
|
entity |
| Predicate | exampleExpression |
P146192
|
FINISHED |
| Object | + 3 4 represents 3 + 4 |
—
|
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: + 3 4 represents 3 + 4 | Statement: [Polish notation, exampleExpression, + 3 4 represents 3 + 4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exampleExpression Context triple: [Polish notation, exampleExpression, + 3 4 represents 3 + 4]
-
A.
coreExpression
Indicates that something is the primary or central expression or representation of another thing.
-
B.
usesExpression
Indicates that one entity employs or applies a particular expression (such as a phrase, symbol, or formula) in its communication or representation.
-
C.
DOCExpression
Indicates that one entity is an expression, representation, or articulation of another entity (such as an idea, concept, or document content).
-
D.
hasExpression
Indicates that an entity displays or possesses a particular facial or emotional expression.
-
E.
typicalExpressionExample
chosen
Indicates that the given expression is a representative or characteristic example of how something is typically expressed or formulated.
- 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_69f348e97fa48190aa06286962af6dee |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6af7f24a881909e6ae0d937e90ea2 |
completed | May 3, 2026, 2:14 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:45 p.m.