Triple
T23808029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MMP |
E589763
|
entity |
| Predicate | typicalThreshold |
P14326
|
FINISHED |
| Object | 5% of party vote in some implementations |
—
|
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: 5% of party vote in some implementations | Statement: [MMP, typicalThreshold, 5% of party vote in some implementations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalThreshold Context triple: [MMP, typicalThreshold, 5% of party vote in some implementations]
-
A.
thresholdFor
chosen
Indicates that one entity specifies the minimum or limiting value at which a condition, effect, or state involving another entity begins to occur or change.
-
B.
typicalPopulationThreshold
Indicates the population level above which a place is typically considered to meet a particular classification or status.
-
C.
typicalRange
Indicates the usual or expected range of values, conditions, or states within which something normally occurs or applies.
-
D.
typicalPerformanceSetting
Indicates the usual or most common context, venue, or environment in which a performance or activity typically takes place.
-
E.
typicalIn
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
- 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_69e25d19fecc8190a5cf39bbb18d5d7f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c753c46081908b3c9e5c2517b051 |
completed | April 29, 2026, 8:54 a.m. |
| PD | Predicate disambiguation | batch_69f155fe300481909bd617443228df65 |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:56 p.m.