Triple
T16282003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vantaa |
E395287
|
entity |
| Predicate | hasNeighbourhood |
P4813
|
FINISHED |
| Object |
Korso
Korso is a residential district and suburban area in the city of Vantaa, Finland.
|
E1203322
|
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: Korso | Statement: [Vantaa, hasNeighbourhood, Korso]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Korso Context triple: [Vantaa, hasNeighbourhood, Korso]
-
A.
Mora
Mora is a surname of Hungarian origin most notably borne by the German-Hungarian writer Terézia Mora.
-
B.
Mora
Mora is a town in central Sweden’s Dalarna region, known for its traditional Swedish culture, proximity to Lake Siljan, and as the finish line of the Vasaloppet cross-country ski race.
-
C.
Mora
Mora is a municipality in Portugal known for its rural Alentejo landscapes, traditional villages, and proximity to the Montargil reservoir.
-
D.
Mora
Mora is a canton in Costa Rica’s San José Province known for its rural landscapes, agricultural activities, and small-town communities.
-
E.
Logudoro
Logudoro is a historical-cultural region in northern Sardinia known for its distinctive Sardinian dialect, medieval heritage, and rural landscapes.
- 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: Korso Triple: [Vantaa, hasNeighbourhood, Korso]
Generated description
Korso is a residential district and suburban area in the city of Vantaa, Finland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Korso Target entity description: Korso is a residential district and suburban area in the city of Vantaa, Finland.
-
A.
Mora
Mora is a town in central Sweden’s Dalarna region, known for its traditional Swedish culture, proximity to Lake Siljan, and as the finish line of the Vasaloppet cross-country ski race.
-
B.
Mora
Mora is a canton in Costa Rica’s San José Province known for its rural landscapes, agricultural activities, and small-town communities.
-
C.
Mora
Mora is a surname of Hungarian origin most notably borne by the German-Hungarian writer Terézia Mora.
-
D.
Mora
Mora is a municipality in Portugal known for its rural Alentejo landscapes, traditional villages, and proximity to the Montargil reservoir.
-
E.
Logudoro
Logudoro is a historical-cultural region in northern Sardinia known for its distinctive Sardinian dialect, medieval heritage, and rural landscapes.
- 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_69d87f22c7248190a54c949738441e2e |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e24910c6b881909ae5cc0908dd8eb2 |
completed | April 17, 2026, 2:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0017c6b72081908a21e5099f463b62 |
completed | May 10, 2026, 5:29 a.m. |
| NEDg | Description generation | batch_6a001876efb081909c0940ebcf265f15 |
completed | May 10, 2026, 5:32 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0018f6de84819087b8e97b0400c77d |
completed | May 10, 2026, 5:34 a.m. |
Created at: April 10, 2026, 5:05 a.m.