Triple
T26893342
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | মাদ্রাজ |
E677835
|
entity |
| Predicate | মুদ্রা |
P245
|
FINISHED |
| Object | ভারতীয় রুপি |
—
|
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: ভারতীয় রুপি | Statement: [মাদ্রাজ, মুদ্রা, ভারতীয় রুপি]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: মুদ্রা Context triple: [মাদ্রাজ, মুদ্রা, ভারতীয় রুপি]
-
A.
currency
chosen
Indicates that one entity serves as the medium of exchange or monetary unit used by another entity (such as a country, region, or system).
-
B.
monetaryFunction
Indicates a relationship where something serves a financial role, such as handling, managing, or affecting money or economic value.
-
C.
monetaryComponent
Indicates that something is a financial element or part of a larger monetary value, structure, or transaction.
-
D.
monetaryUnitOfAccount
Indicates that something serves as the standard unit in which the value of goods, services, and financial transactions is measured and recorded.
-
E.
अर्थ
Indicates a semantic or conceptual meaning relationship between entities, where one entity represents or conveys the sense or significance of another.
- 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_69eee9befee48190a26f214faa867be7 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f61f69e4508190ab20c3f2052282e7 |
completed | May 2, 2026, 3:59 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 5:46 a.m.