Triple
T22133813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haderslev Dam |
E546972
|
entity |
| Predicate | watercourse |
P415
|
FINISHED |
| Object |
Haderslev Å
Haderslev Å is a river in southern Denmark that flows through the town of Haderslev and into Haderslev Dam before reaching the Little Belt.
|
E1519866
|
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: Haderslev Å | Statement: [Haderslev Dam, watercourse, Haderslev Å]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Haderslev Å Context triple: [Haderslev Dam, watercourse, Haderslev Å]
-
A.
Kolding River
Kolding River is a watercourse in southern Denmark that flows through the city of Kolding before emptying into Kolding Fjord.
-
B.
Vejle River
Vejle River is a Danish watercourse in Jutland known for flowing through the town of Vejle and its surrounding valley before emptying into Vejle Fjord.
-
C.
Odense River
The Odense River is a waterway on the Danish island of Funen that flows through the city of Odense before emptying into Odense Fjord.
-
D.
Aarhus Å
Aarhus Å is a small river running through the Danish city of Aarhus before emptying into Aarhus Bay.
-
E.
Venø
Venø is a small Danish island in the Limfjord known for its scenic landscapes, birdlife, and traditional coastal village atmosphere.
- 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: Haderslev Å Triple: [Haderslev Dam, watercourse, Haderslev Å]
Generated description
Haderslev Å is a river in southern Denmark that flows through the town of Haderslev and into Haderslev Dam before reaching the Little Belt.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Haderslev Å Target entity description: Haderslev Å is a river in southern Denmark that flows through the town of Haderslev and into Haderslev Dam before reaching the Little Belt.
-
A.
Kolding River
Kolding River is a watercourse in southern Denmark that flows through the city of Kolding before emptying into Kolding Fjord.
-
B.
Vejle River
Vejle River is a Danish watercourse in Jutland known for flowing through the town of Vejle and its surrounding valley before emptying into Vejle Fjord.
-
C.
Odense River
The Odense River is a waterway on the Danish island of Funen that flows through the city of Odense before emptying into Odense Fjord.
-
D.
Aarhus Å
Aarhus Å is a small river running through the Danish city of Aarhus before emptying into Aarhus Bay.
-
E.
Venø
Venø is a small Danish island in the Limfjord known for its scenic landscapes, birdlife, and traditional coastal village atmosphere.
- 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_69e11e39bf348190b541bfa16a7b71e0 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129b81d5c819085fd18bf3ae28333 |
completed | April 28, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a8f2bd49c81908a75359074a0ada2 |
completed | May 18, 2026, 4:01 a.m. |
| NEDg | Description generation | batch_6a0a91ef8d188190a6ec20d6c43aef91 |
completed | May 18, 2026, 4:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a9266624c81908eb06a0fc02b85d4 |
completed | May 18, 2026, 4:15 a.m. |
Created at: April 16, 2026, 8:32 p.m.