Triple
T29904389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | magic formula (Swiss party power-sharing) |
E759495
|
entity |
| Predicate | originalFormulaRatio |
P136958
|
FINISHED |
| Object | 2–2–2–1 |
—
|
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: 2–2–2–1 | Statement: [magic formula (Swiss party power-sharing), originalFormulaRatio, 2–2–2–1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalFormulaRatio Context triple: [magic formula (Swiss party power-sharing), originalFormulaRatio, 2–2–2–1]
-
A.
primaryFormulaFormat
Indicates the main or default structural format in which a formula is represented or stored.
-
B.
alternativeRatio
chosen
Indicates the proportion or comparative share between different alternative options within a given context.
-
C.
keyFormula
Indicates that a formula serves as the primary or defining expression associated with an entity or relationship.
-
D.
formulaInvolves
Indicates that a given formula includes, references, or depends on a specified element or component.
-
E.
typicalIngredientRatio
Indicates the usual proportional relationship between different ingredients used together in a preparation or mixture.
- 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_69f224600590819085e148a01c056ef6 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fff09dae088190bd8460060d778feb |
completed | May 10, 2026, 2:42 a.m. |
| PD | Predicate disambiguation | batch_69fff0027c5c8190baa5c7a15852cbe0 |
completed | May 10, 2026, 2:40 a.m. |
Created at: April 29, 2026, 6:07 p.m.