Triple
T34819355
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tariff of 1842 |
E1003724
|
entity |
| Predicate | averageRate |
P132852
|
FINISHED |
| Object | approximately 32 percent ad valorem |
—
|
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: approximately 32 percent ad valorem | Statement: [Tariff of 1842, averageRate, approximately 32 percent ad valorem]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: averageRate Context triple: [Tariff of 1842, averageRate, approximately 32 percent ad valorem]
-
A.
averageOrder
Indicates the typical or mean value of orders associated with an entity over a given set or period.
-
B.
averageAge
Indicates the mean age value calculated from a group of entities or individuals.
-
C.
aggregateRate
chosen
Indicates a combined or overall rate derived from multiple individual rates or components.
-
D.
typicalRate
Indicates the standard or commonly expected rate at which something occurs, is charged, or is applied in a given context.
-
E.
baseRate
Indicates the fundamental or standard rate at which something occurs or is charged, serving as a baseline before adjustments or modifiers are applied.
- 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_69f76db717088190811b4e744610f37d |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f77adc1f9c81909f747e68561e29c9 |
completed | May 3, 2026, 4:42 p.m. |
| PD | Predicate disambiguation | batch_69f7795b1abc8190823664d1caa94649 |
completed | May 3, 2026, 4:35 p.m. |
Created at: May 3, 2026, 4 p.m.