Triple
T8703305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pellinge archipelago |
E206585
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Sandholmen
Sandholmen is an island within Finland’s Pellinge archipelago, known for its coastal nature and maritime surroundings.
|
E751405
|
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: Sandholmen | Statement: [Pellinge archipelago, hasPart, Sandholmen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandholmen Context triple: [Pellinge archipelago, hasPart, Sandholmen]
-
A.
Nakkholmen
Nakkholmen is a small inhabited island known for its traditional wooden cabins and recreational use, located in the Oslofjord near Oslo, Norway.
-
B.
Kvarnholmen
Kvarnholmen is a former industrial island district in the Stockholm area that has been transformed into a modern residential and waterfront neighborhood.
-
C.
Gressholmen
Gressholmen is a small recreational island near central Oslo, Norway, known for its beaches, nature reserve areas, and former seaplane airport.
-
D.
Skärholmen
Skärholmen is a suburban district in southwestern Stockholm, Sweden, known for its large shopping center and residential areas.
-
E.
Vaxholmen island
Vaxholmen island is a small island in the Stockholm archipelago of Sweden, historically significant as the site of the coastal defense stronghold Vaxholm Fortress.
- 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: Sandholmen Triple: [Pellinge archipelago, hasPart, Sandholmen]
Generated description
Sandholmen is an island within Finland’s Pellinge archipelago, known for its coastal nature and maritime surroundings.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sandholmen Target entity description: Sandholmen is an island within Finland’s Pellinge archipelago, known for its coastal nature and maritime surroundings.
-
A.
Nakkholmen
Nakkholmen is a small inhabited island known for its traditional wooden cabins and recreational use, located in the Oslofjord near Oslo, Norway.
-
B.
Kvarnholmen
Kvarnholmen is a former industrial island district in the Stockholm area that has been transformed into a modern residential and waterfront neighborhood.
-
C.
Gressholmen
Gressholmen is a small recreational island near central Oslo, Norway, known for its beaches, nature reserve areas, and former seaplane airport.
-
D.
Skärholmen
Skärholmen is a suburban district in southwestern Stockholm, Sweden, known for its large shopping center and residential areas.
-
E.
Vaxholmen island
Vaxholmen island is a small island in the Stockholm archipelago of Sweden, historically significant as the site of the coastal defense stronghold Vaxholm Fortress.
- 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_69ca835645e881908f00e3c8b51da81d |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc58fa0a208190a520e0e1f7faaea9 |
completed | March 31, 2026, 11:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cef41e3ec08190b29adf483cdf8cc3 |
completed | April 2, 2026, 10:56 p.m. |
| NEDg | Description generation | batch_69cef68b33948190a259870e320da5e5 |
completed | April 2, 2026, 11:06 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cef6fb42e48190b09d49d3a2fee4ae |
completed | April 2, 2026, 11:08 p.m. |
Created at: March 30, 2026, 6:34 p.m.