Triple
T16341801
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lomaiviti Islands |
E396823
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object | Batiki |
E1143117
|
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: Batiki | Statement: [Lomaiviti Islands, hasIsland, Batiki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Batiki Context triple: [Lomaiviti Islands, hasIsland, Batiki]
-
A.
Batiki
chosen
Batiki is a small inhabited island in Fiji’s Lomaiviti archipelago, known for its traditional villages, copra production, and kava (yaqona) farming.
-
B.
Batanta
Batanta is one of the main islands of Indonesia’s Raja Ampat (Papuan) archipelago, known for its rich marine biodiversity and lush, sparsely populated rainforest.
-
C.
Baganga
Baganga is a coastal municipality in the province of Davao Oriental in the Philippines, known for its beaches, waterfalls, and rich marine and forest resources.
-
D.
Basoko
Basoko is a riverside town in the Democratic Republic of the Congo, situated at the confluence of the Aruwimi and Congo Rivers and serving as a local administrative and trading center.
-
E.
Berbeka
Berbeka is a Polish surname most notably associated with high-altitude mountaineer Maciej Berbeka.
- 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2da0ad510819082e440f5e2bceada |
completed | April 18, 2026, 1:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00261cf0648190b4dd5ff79de7e315 |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 5:07 a.m.