Triple
T116270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Australian dollar |
E2344
|
entity |
| Predicate | ISOStandard |
P1587
|
FINISHED |
| Object | ISO 4217 |
E10239
|
NE 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: ISO 4217 | Statement: [Australian dollar, ISOStandard, ISO 4217]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ISO 4217 Context triple: [Australian dollar, ISOStandard, ISO 4217]
-
A.
ISO 4217
chosen
ISO 4217 is the international standard that defines three-letter codes and related data for the representation of currencies and funds worldwide.
-
B.
ISO 3166-1
ISO 3166-1 is an international standard published by ISO that defines globally recognized country codes in alpha-2, alpha-3, and numeric formats.
-
C.
ISO 3166 Maintenance Agency
The ISO 3166 Maintenance Agency is the international body responsible for developing and updating the ISO 3166 standard that defines country codes and their subdivisions.
-
D.
SWIFT
SWIFT is a global financial messaging network that enables secure, standardized communication and transaction instructions between banks and other financial institutions worldwide.
-
E.
ISO 3166-1 numeric
ISO 3166-1 numeric is the part of the ISO 3166 standard that assigns three-digit numeric country codes used internationally for data processing and classification.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a2506c5428819085c28a8884790e29 |
completed | Feb. 28, 2026, 2:18 a.m. |
| NER | Named-entity recognition | batch_69a25b800d08819099a44429d5c82c68 |
completed | Feb. 28, 2026, 3:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a285012e5881909b19f6c49a2373e1 |
completed | Feb. 28, 2026, 6:02 a.m. |
Created at: Feb. 28, 2026, 2:24 a.m.