Triple
T320695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Korean won |
E6407
|
entity |
| Predicate | hasBanknoteDenomination |
P2871
|
FINISHED |
| Object | 1000 won |
—
|
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: 1000 won | Statement: [South Korean won, hasBanknoteDenomination, 1000 won]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBanknoteDenomination Context triple: [South Korean won, hasBanknoteDenomination, 1000 won]
-
A.
banknoteDenomination
chosen
Indicates the specific face value assigned to a banknote in a given currency.
-
B.
typeOfBanknotes
Indicates a relationship where one entity specifies the kind or category of banknotes associated with another entity.
-
C.
denominationType
Indicates the specific category or kind of denomination associated with an entity, such as its type within a broader classification of denominations.
-
D.
denomination
Indicates the specific religious or organizational branch, sect, or subgroup with which an entity is affiliated.
-
E.
currentBanknoteSeries
Indicates that the subject is part of, or associated with, the banknote series that is currently in official circulation.
- 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_69a2e7933d6c8190bb2592ad13286ef2 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2ea8047c08190872c875e00f6e7dd |
completed | Feb. 28, 2026, 1:15 p.m. |
| PD | Predicate disambiguation | batch_69a2e946607081909c8b97473aaf8d1b |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.