Triple
T870721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danske Bank |
E18805
|
entity |
| Predicate | headquartersLocation |
P62
|
FINISHED |
| Object | Copenhagen |
E12606
|
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: Copenhagen | Statement: [Danske Bank, headquartersLocation, Copenhagen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Copenhagen Context triple: [Danske Bank, headquartersLocation, Copenhagen]
-
A.
Copenhagen
chosen
Copenhagen is the capital and largest city of Denmark, known for its historic architecture, vibrant cultural scene, and high quality of life.
-
B.
Aarhus
Aarhus is Denmark’s second-largest city, a major cultural and economic center on the Jutland peninsula known for its universities, vibrant arts scene, and historic harbor.
-
C.
Herning
Herning is a Danish city in the Central Jutland region known for its trade fairs, conference facilities, and vibrant cultural and sports events.
-
D.
Oslo
Oslo is the capital and largest city of Norway, known as a major cultural, economic, and governmental center.
-
E.
Hillerød
Hillerød is a Danish town on the island of Zealand, known for the historic Frederiksborg Castle and its role as a regional administrative and cultural center.
- 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_69a4938db1f081909bcd1ad2713b6096 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac94d5ac81909feee876696da589 |
completed | March 1, 2026, 9:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7c01af9608190b3b735c590024f03 |
completed | March 4, 2026, 5:16 a.m. |
Created at: March 1, 2026, 7:39 p.m.