Triple
T21032590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hisingen |
E518099
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Lundby
Lundby is a district on the island of Hisingen in Gothenburg, Sweden, known for its mix of residential areas, industry, and waterfront locations along the Göta älv river.
|
E1469467
|
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: Lundby | Statement: [Hisingen, contains, Lundby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lundby Context triple: [Hisingen, contains, Lundby]
-
A.
Sundby
Sundby is a district on the island of Amager in Copenhagen, Denmark, encompassing the neighborhoods of Sundbyvester and Sundbyøster.
-
B.
Gårdby
Gårdby is a small village on the island of Öland in southeastern Sweden, known for its rural landscape and traditional Swedish countryside character.
-
C.
Rødby
Rødby is a small town on the Danish island of Lolland, known historically as a ferry port linking Denmark and Germany across the Baltic Sea.
-
D.
Vårby
Vårby is a suburban district in the southern Stockholm area of Sweden, known for its residential neighborhoods and proximity to Lake Mälaren.
-
E.
Kirkeby
Kirkeby is a small settlement located on the Danish island of Bornholm within Bornholm Municipality.
- 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: Lundby Triple: [Hisingen, contains, Lundby]
Generated description
Lundby is a district on the island of Hisingen in Gothenburg, Sweden, known for its mix of residential areas, industry, and waterfront locations along the Göta älv river.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lundby Target entity description: Lundby is a district on the island of Hisingen in Gothenburg, Sweden, known for its mix of residential areas, industry, and waterfront locations along the Göta älv river.
-
A.
Sundby
Sundby is a district on the island of Amager in Copenhagen, Denmark, encompassing the neighborhoods of Sundbyvester and Sundbyøster.
-
B.
Gårdby
Gårdby is a small village on the island of Öland in southeastern Sweden, known for its rural landscape and traditional Swedish countryside character.
-
C.
Rødby
Rødby is a small town on the Danish island of Lolland, known historically as a ferry port linking Denmark and Germany across the Baltic Sea.
-
D.
Vårby
Vårby is a suburban district in the southern Stockholm area of Sweden, known for its residential neighborhoods and proximity to Lake Mälaren.
-
E.
Kirkeby
Kirkeby is a small settlement located on the Danish island of Bornholm within Bornholm Municipality.
- 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_69e0b503275c8190afd9a163f997c709 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc83828c81909c1ec745c0313c9f |
completed | April 21, 2026, 4:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a096dacc2788190b6f6be0962936781 |
completed | May 17, 2026, 7:26 a.m. |
| NEDg | Description generation | batch_6a097190702c8190ab46fc8762c0d4be |
completed | May 17, 2026, 7:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0971eae3148190ac998691099dfba8 |
completed | May 17, 2026, 7:44 a.m. |
Created at: April 16, 2026, 1:56 p.m.