Triple
T7793253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gressholmen |
E180232
|
entity |
| Predicate | isNear |
P350
|
FINISHED |
| Object |
Heggholmen
Heggholmen is a small island in the Oslofjord near Oslo, Norway, known for its coastal scenery and proximity to other islets like Gressholmen.
|
E693937
|
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: Heggholmen | Statement: [Gressholmen, isNear, Heggholmen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heggholmen Context triple: [Gressholmen, isNear, Heggholmen]
-
A.
Helgeandsholmen
Helgeandsholmen is a small central Stockholm islet best known as the site of the Swedish Parliament building and part of the historic city core.
-
B.
Røsholmholmen
Røsholmholmen is a small island located in Tyrifjorden, a large lake in southeastern Norway.
-
C.
Gressholmen
Gressholmen is a small recreational island near central Oslo, Norway, known for its beaches, nature reserve areas, and former seaplane airport.
-
D.
Sprogø
Sprogø is a small Danish island in the Great Belt known for its strategic location and role as a central support point for the Great Belt Bridge connecting Zealand and Funen.
-
E.
Hvidøen
Hvidøen is the former name of Kvitøya, a remote, ice-covered island in the Svalbard archipelago of the Arctic Ocean.
- 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: Heggholmen Triple: [Gressholmen, isNear, Heggholmen]
Generated description
Heggholmen is a small island in the Oslofjord near Oslo, Norway, known for its coastal scenery and proximity to other islets like Gressholmen.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Heggholmen Target entity description: Heggholmen is a small island in the Oslofjord near Oslo, Norway, known for its coastal scenery and proximity to other islets like Gressholmen.
-
A.
Helgeandsholmen
Helgeandsholmen is a small central Stockholm islet best known as the site of the Swedish Parliament building and part of the historic city core.
-
B.
Røsholmholmen
Røsholmholmen is a small island located in Tyrifjorden, a large lake in southeastern Norway.
-
C.
Gressholmen
Gressholmen is a small recreational island near central Oslo, Norway, known for its beaches, nature reserve areas, and former seaplane airport.
-
D.
Sprogø
Sprogø is a small Danish island in the Great Belt known for its strategic location and role as a central support point for the Great Belt Bridge connecting Zealand and Funen.
-
E.
Hvidøen
Hvidøen is the former name of Kvitøya, a remote, ice-covered island in the Svalbard archipelago of the Arctic Ocean.
- 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_69ca827d22208190b4dc5aa680edcf5d |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cae939c7388190b36d3e746be27a4d |
completed | March 30, 2026, 9:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb13dbe1f88190bde2c5c76dcfeb8f |
completed | March 31, 2026, 12:22 a.m. |
| NEDg | Description generation | batch_69cb1730900c8190bc0322c4b6a3772f |
completed | March 31, 2026, 12:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cb1a29d2988190bb64aada0d2ef463 |
completed | March 31, 2026, 12:49 a.m. |
Created at: March 30, 2026, 4:31 p.m.