Triple
T22460652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | International Financial Services |
E555218
|
entity |
| Predicate | parentCompanyTicker |
P21787
|
FINISHED |
| Object | BNP |
—
|
NE NERFINISHED |
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: BNP | Statement: [International Financial Services, parentCompanyTicker, BNP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BNP Context triple: [International Financial Services, parentCompanyTicker, BNP]
-
A.
BNP
chosen
BNP is the stock ticker symbol for BNP Paribas, a major French international banking and financial services group.
-
B.
BNP
BNP is the National Rail station code assigned to Barnstaple railway station in Devon, England.
-
C.
BNP
BNP is the three-letter IATA airport code assigned to Bannu Airport in Pakistan.
-
D.
BNP
BNP is the National Library of Peru, the country’s principal public institution responsible for preserving and providing access to its documentary and bibliographic heritage.
-
E.
BNP
BNP is the acronym commonly used to refer to the National Library of Portugal, the country’s main institution for preserving and providing access to its bibliographic heritage.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b7eb5688190bd5e41d4d8189668 |
completed | April 29, 2026, 1:14 a.m. |
Created at: April 16, 2026, 8:48 p.m.