Triple
T17117119
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biograd na Moru |
E415367
|
entity |
| Predicate | hasHarbor |
P3007
|
FINISHED |
| Object | Biograd harbor |
E1251753
|
NE FINISHED |
How this triple was built (2 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: Biograd harbor | Statement: [Biograd na Moru, hasHarbor, Biograd harbor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Biograd harbor Context triple: [Biograd na Moru, hasHarbor, Biograd harbor]
-
A.
Crikvenica harbor
Crikvenica harbor is a coastal port and marina on Croatia’s Adriatic coast, serving as a hub for local fishing, tourism, and recreational boating.
-
B.
Biograd na Moru port
chosen
Biograd na Moru port is a coastal marina and harbor on Croatia’s Adriatic Sea, serving as a popular hub for nautical tourism and local maritime activities.
-
C.
Port of Rijeka
The Port of Rijeka is Croatia’s largest seaport and a major Adriatic maritime hub for cargo and passenger transport.
-
D.
Kraljevica port
Kraljevica port is a coastal harbor in the town of Kraljevica, Croatia, serving local maritime traffic and tourism on the Adriatic Sea.
-
E.
Port of Zadar
The Port of Zadar is a key Croatian Adriatic seaport serving passenger ferries, cargo traffic, and tourism for the city of Zadar and its surrounding islands.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d886d090cc8190a39cb94992586905 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3e80660048190832d8f91415dd7d7 |
completed | April 18, 2026, 8:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a014145f7988190803d5c5e4f2705b0 |
completed | May 11, 2026, 2:39 a.m. |
Created at: April 10, 2026, 5:35 a.m.