Triple
T9574865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BNM |
E231019
|
entity |
| Predicate | hasAbbreviation |
P43
|
FINISHED |
| Object | BNM |
E231019
|
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: BNM | Statement: [BNM, hasAbbreviation, BNM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BNM Context triple: [BNM, hasAbbreviation, BNM]
-
A.
BNM
chosen
BNM is the central bank of Malaysia, responsible for issuing currency, formulating monetary policy, and overseeing the country’s financial system.
-
B.
BNR
BNR is the central bank of Romania, responsible for the country’s monetary policy, currency issuance, and financial system stability.
-
C.
MNB
MNB is the central bank of Hungary, responsible for the country’s monetary policy, financial stability, and issuance of the national currency.
-
D.
NBP
NBP is a protocol used in AppleTalk networks to map human-readable names to network addresses, enabling devices and services to be discovered and accessed.
-
E.
NBP
NBP is the commonly used abbreviation for the New Bilibid Prison, the Philippines’ main national penitentiary located in Muntinlupa City.
- 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_69ca848091c48190bc313d6620d09555 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd99aa964c8190a50717edff30f10b |
completed | April 1, 2026, 10:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d152c3f1e8819099f3f9d0f1d2d7b3 |
completed | April 4, 2026, 6:04 p.m. |
Created at: March 30, 2026, 8:05 p.m.