Triple
T19924189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vela Luka |
E478880
|
entity |
| Predicate | nearbyIsland |
P2064
|
FINISHED |
| Object |
Proizd
Proizd is a small, scenic Croatian island in the Adriatic Sea known for its clear turquoise waters, rocky beaches, and tranquil natural setting.
|
E1402194
|
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: Proizd | Statement: [Vela Luka, nearbyIsland, Proizd]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Proizd Context triple: [Vela Luka, nearbyIsland, Proizd]
-
A.
Prostki
Prostki is a village in northeastern Poland, known for its historical significance and location within the Warmian-Masurian Voivodeship.
-
B.
Proz
Proz is a musical artist known for contributing featured vocals to the track "Birth of a Prince."
-
C.
Prost
Prost is a French surname most famously associated with Formula One world champion Alain Prost.
-
D.
Preki
Preki is a former Yugoslav-American professional soccer player and coach best known for his standout MLS career and successful transition into coaching.
-
E.
Aproz
Aproz is a village in the municipality of Nendaz in the canton of Valais, Switzerland, known for its mineral water production and location in the Rhône valley.
- 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: Proizd Triple: [Vela Luka, nearbyIsland, Proizd]
Generated description
Proizd is a small, scenic Croatian island in the Adriatic Sea known for its clear turquoise waters, rocky beaches, and tranquil natural setting.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Proizd Target entity description: Proizd is a small, scenic Croatian island in the Adriatic Sea known for its clear turquoise waters, rocky beaches, and tranquil natural setting.
-
A.
Prostki
Prostki is a village in northeastern Poland, known for its historical significance and location within the Warmian-Masurian Voivodeship.
-
B.
Proz
Proz is a musical artist known for contributing featured vocals to the track "Birth of a Prince."
-
C.
Prost
Prost is a French surname most famously associated with Formula One world champion Alain Prost.
-
D.
Preki
Preki is a former Yugoslav-American professional soccer player and coach best known for his standout MLS career and successful transition into coaching.
-
E.
Aproz
Aproz is a village in the municipality of Nendaz in the canton of Valais, Switzerland, known for its mineral water production and location in the Rhône valley.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659c88c548190b9b9eccbdd07d977 |
completed | April 20, 2026, 4:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07ea56ae608190815a66c89dadcb9e |
completed | May 16, 2026, 3:53 a.m. |
| NEDg | Description generation | batch_6a07f2bc1474819092902f88b3309e0d |
completed | May 16, 2026, 4:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07f376f5388190989a0460528945df |
completed | May 16, 2026, 4:32 a.m. |
Created at: April 10, 2026, 1:53 p.m.