Triple
T8591815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parainen |
E203444
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object |
Korpo
Korpo is a large island in Finland’s southwestern archipelago, known for its coastal landscapes, small villages, and role as part of the municipality of Parainen.
|
E745230
|
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: Korpo | Statement: [Parainen, hasIsland, Korpo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Korpo Context triple: [Parainen, hasIsland, Korpo]
-
A.
Korvel
Korvel is a residential neighborhood in the Dutch city of Tilburg, known for its mix of urban housing, local shops, and multicultural character.
-
B.
Konerko
Konerko is the surname of Paul Konerko, a former Major League Baseball first baseman best known for his long tenure and leadership with the Chicago White Sox.
-
C.
Kors
Kors is the surname of American fashion designer Michael Kors, known for his eponymous luxury brand.
-
D.
Kungara
Kungara is an alternative name for the Fur language, a Nilo-Saharan language spoken primarily by the Fur people of western Sudan.
-
E.
Burcorps
Burcorps is an alternative name for the Burma Corps, a British Indian Army formation that operated in the Burma Campaign during World War II.
- 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: Korpo Triple: [Parainen, hasIsland, Korpo]
Generated description
Korpo is a large island in Finland’s southwestern archipelago, known for its coastal landscapes, small villages, and role as part of the municipality of Parainen.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Korpo Target entity description: Korpo is a large island in Finland’s southwestern archipelago, known for its coastal landscapes, small villages, and role as part of the municipality of Parainen.
-
A.
Korvel
Korvel is a residential neighborhood in the Dutch city of Tilburg, known for its mix of urban housing, local shops, and multicultural character.
-
B.
Konerko
Konerko is the surname of Paul Konerko, a former Major League Baseball first baseman best known for his long tenure and leadership with the Chicago White Sox.
-
C.
Kors
Kors is the surname of American fashion designer Michael Kors, known for his eponymous luxury brand.
-
D.
Kungara
Kungara is an alternative name for the Fur language, a Nilo-Saharan language spoken primarily by the Fur people of western Sudan.
-
E.
Burcorps
Burcorps is an alternative name for the Burma Corps, a British Indian Army formation that operated in the Burma Campaign during World War II.
- 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_69ca832a7f108190b4e4f5648abf4aa2 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc466747b88190b752f78f361140cb |
completed | March 31, 2026, 10:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cea8b584088190bc5b8b2785894d82 |
completed | April 2, 2026, 5:34 p.m. |
| NEDg | Description generation | batch_69cea9cff1ec8190a0093fb42782341e |
completed | April 2, 2026, 5:39 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ceaa9f7f8c8190965e86880ff141d5 |
completed | April 2, 2026, 5:42 p.m. |
Created at: March 30, 2026, 6:23 p.m.