Triple
T885040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Croatia |
E19110
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object |
Korčula
Korčula is a historic Adriatic island known for its medieval walled town, dense forests, and rich Croatian cultural heritage.
|
E110307
|
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: Korčula | Statement: [Croatia, hasIsland, Korčula]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Korčula Context triple: [Croatia, hasIsland, Korčula]
-
A.
Hvar
Hvar is a popular Croatian island in the Adriatic Sea known for its sunny climate, historic town, lavender fields, and vibrant nightlife.
-
B.
Brač
Brač is a large Adriatic island in Croatia known for its white-pebble Zlatni Rat beach and historic stone masonry.
-
C.
Zadar
Zadar is a historic coastal city in Croatia on the Adriatic Sea, known for its Roman and Venetian ruins, medieval churches, and modern seaside installations like the Sea Organ.
-
D.
Rovinj
Rovinj is a picturesque coastal town on Croatia’s Istrian peninsula, known for its colorful old town, fishing harbor, and popular seaside tourism.
-
E.
Ragusa
Ragusa is a historic baroque hilltop city in southeastern Sicily, Italy, renowned for its UNESCO-listed old town and distinctive architecture.
- 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: Korčula Triple: [Croatia, hasIsland, Korčula]
Generated description
Korčula is a historic Adriatic island known for its medieval walled town, dense forests, and rich Croatian cultural heritage.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Korčula Target entity description: Korčula is a historic Adriatic island known for its medieval walled town, dense forests, and rich Croatian cultural heritage.
-
A.
Hvar
Hvar is a popular Croatian island in the Adriatic Sea known for its sunny climate, historic town, lavender fields, and vibrant nightlife.
-
B.
Brač
Brač is a large Adriatic island in Croatia known for its white-pebble Zlatni Rat beach and historic stone masonry.
-
C.
Zadar
Zadar is a historic coastal city in Croatia on the Adriatic Sea, known for its Roman and Venetian ruins, medieval churches, and modern seaside installations like the Sea Organ.
-
D.
Rovinj
Rovinj is a picturesque coastal town on Croatia’s Istrian peninsula, known for its colorful old town, fishing harbor, and popular seaside tourism.
-
E.
Ragusa
Ragusa is a historic baroque hilltop city in southeastern Sicily, Italy, renowned for its UNESCO-listed old town and distinctive architecture.
- 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_69a4939c32488190a7ccd41cf0abb22b |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ace5e15c81908cc2e648c9cd52f2 |
completed | March 1, 2026, 9:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7ee0053d88190be8705b42d172ab7 |
completed | March 4, 2026, 8:32 a.m. |
| NEDg | Description generation | batch_69a7f91fa98c81908461b9b29db18eb3 |
completed | March 4, 2026, 9:19 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a7f997edb081909d82b13ec88d3f9f |
completed | March 4, 2026, 9:21 a.m. |
Created at: March 1, 2026, 7:39 p.m.