Triple
T9079198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanna |
E217569
|
entity |
| Predicate | hasPort |
P35
|
FINISHED |
| Object | Lenakel |
E168148
|
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: Lenakel | Statement: [Tanna, hasPort, Lenakel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lenakel Context triple: [Tanna, hasPort, Lenakel]
-
A.
Lenakel
chosen
Lenakel is an Oceanic language spoken primarily on Tanna Island in Vanuatu.
-
B.
Tjørnuvík
Tjørnuvík is a small, picturesque coastal village in the Faroe Islands, known for its dramatic surrounding mountains, black sand beach, and views of the sea stacks Risin og Kellingin.
-
C.
Hinnøya
Hinnøya is the largest island in mainland Norway, known for its dramatic fjords, mountains, and coastal landscapes in the north of the country.
-
D.
Rognøya
Rognøya is an island located in the Norwegian lake Norsjø, known as part of the inland archipelago in Telemark.
-
E.
Åndalsnes
Åndalsnes is a small Norwegian town known as a gateway to dramatic fjord and mountain landscapes, including popular hiking and climbing areas like Romsdalseggen and Trollveggen.
- 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_69ca83d6c14c8190bc056d927f00a2a2 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc95c93ee48190842623b57e50f4cf |
completed | April 1, 2026, 3:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d017baebb881908cfecd3438a17166 |
completed | April 3, 2026, 7:40 p.m. |
Created at: March 30, 2026, 7:12 p.m.