Triple
T18424125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vis |
E442093
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object |
Komiža
Komiža is a small coastal town and fishing port on the western side of the Croatian island of Vis in the Adriatic Sea.
|
E1326198
|
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: Komiža | Statement: [Vis, hasSettlement, Komiža]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Komiža Context triple: [Vis, hasSettlement, Komiža]
-
A.
Kuzminki
Kuzminki is a Moscow Metro station on the Tagansko–Krasnopresnenskaya Line serving the Kuzminki District in southeastern Moscow.
-
B.
Slanica
Slanica was a former Slovak village in the Orava region that was submerged during the creation of the Orava Reservoir, with only its church preserved on an island as a memorial.
-
C.
Zahumlje
Zahumlje was a medieval South Slavic principality located along the Adriatic coast in the western Balkans, roughly corresponding to parts of modern-day Herzegovina and southern Dalmatia.
-
D.
Korenica
Korenica is a small town in central Croatia that serves as an administrative and service center near the Plitvice Lakes National Park.
-
E.
Kapesovo
Kapesovo is a traditional stone-built village in the Zagori region of Epirus, Greece, known for its preserved architecture and scenic mountainous setting.
- 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: Komiža Triple: [Vis, hasSettlement, Komiža]
Generated description
Komiža is a small coastal town and fishing port on the western side of the Croatian island of Vis in the Adriatic Sea.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Komiža Target entity description: Komiža is a small coastal town and fishing port on the western side of the Croatian island of Vis in the Adriatic Sea.
-
A.
Kuzminki
Kuzminki is a Moscow Metro station on the Tagansko–Krasnopresnenskaya Line serving the Kuzminki District in southeastern Moscow.
-
B.
Slanica
Slanica was a former Slovak village in the Orava region that was submerged during the creation of the Orava Reservoir, with only its church preserved on an island as a memorial.
-
C.
Zahumlje
Zahumlje was a medieval South Slavic principality located along the Adriatic coast in the western Balkans, roughly corresponding to parts of modern-day Herzegovina and southern Dalmatia.
-
D.
Korenica
Korenica is a small town in central Croatia that serves as an administrative and service center near the Plitvice Lakes National Park.
-
E.
Kapesovo
Kapesovo is a traditional stone-built village in the Zagori region of Epirus, Greece, known for its preserved architecture and scenic mountainous setting.
- 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_69d8b9eb8a508190a942fd75ebd8b1dc |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e51b102dd88190af474902fe58ead5 |
completed | April 19, 2026, 6:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a043f1a0f108190a81e26728e367e7e |
completed | May 13, 2026, 9:06 a.m. |
| NEDg | Description generation | batch_6a044044109c8190a767a0ac29a95f53 |
completed | May 13, 2026, 9:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a04411b29048190807604f3687a56a0 |
completed | May 13, 2026, 9:15 a.m. |
Created at: April 10, 2026, 10:47 a.m.