Triple
T14222179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swiss Federal Office of Culture |
E352523
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object |
BAK
BAK is the acronym for the Swiss Federal Office of Culture, the national authority responsible for promoting and preserving Switzerland’s cultural heritage and arts.
|
E1088580
|
NE FINISHED |
How this triple was built (4 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: BAK | Statement: [Swiss Federal Office of Culture, abbreviation, BAK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BAK Context triple: [Swiss Federal Office of Culture, abbreviation, BAK]
-
A.
BAK
BAK is the National Rail station code used to identify Baker Street station in London’s rail network.
-
B.
BAKIZA
BAKIZA is the official Swahili language council of Zanzibar responsible for promoting, standardizing, and developing Kiswahili in the region.
-
C.
BAKred
BAKred was the abbreviated name of Germany’s former Federal Banking Supervisory Office, the national authority responsible for overseeing and regulating the banking sector before its functions were integrated into BaFin.
-
D.
Bakar
Bakar is a historic coastal town and port on the Adriatic Sea in western Croatia.
-
E.
Bakish
Bakish is the surname of Bob Bakish, an American media executive best known as the former president and CEO of Paramount Global (formerly ViacomCBS).
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: BAK Triple: [Swiss Federal Office of Culture, abbreviation, BAK]
Generated description
BAK is the acronym for the Swiss Federal Office of Culture, the national authority responsible for promoting and preserving Switzerland’s cultural heritage and arts.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: BAK Target entity description: BAK is the acronym for the Swiss Federal Office of Culture, the national authority responsible for promoting and preserving Switzerland’s cultural heritage and arts.
-
A.
BAK
BAK is the National Rail station code used to identify Baker Street station in London’s rail network.
-
B.
BAKIZA
BAKIZA is the official Swahili language council of Zanzibar responsible for promoting, standardizing, and developing Kiswahili in the region.
-
C.
BAKred
BAKred was the abbreviated name of Germany’s former Federal Banking Supervisory Office, the national authority responsible for overseeing and regulating the banking sector before its functions were integrated into BaFin.
-
D.
Bakar
Bakar is a historic coastal town and port on the Adriatic Sea in western Croatia.
-
E.
Bakish
Bakish is the surname of Bob Bakish, an American media executive best known as the former president and CEO of Paramount Global (formerly ViacomCBS).
- F. None of above. chosen
Provenance (5 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_69d8278a06e481908b5d6af0a8afe737 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6213801c8190a47705cd890b9ae7 |
completed | April 14, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd2813e55881909bdbc6f3c6ef572b |
completed | May 8, 2026, 12:02 a.m. |
| NEDg | Description generation | batch_69fd2b0956948190bf654403ad0b154a |
completed | May 8, 2026, 12:15 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd2df66aa48190ae18a4ca1c099c25 |
completed | May 8, 2026, 12:27 a.m. |
Created at: April 10, 2026, 1:06 a.m.