Triple
T14216017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kadavu musk parrot |
E352352
|
entity |
| Predicate | foundOnIsland |
P35221
|
FINISHED |
| Object | Kadavu |
E71296
|
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: Kadavu | Statement: [Kadavu musk parrot, foundOnIsland, Kadavu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kadavu Context triple: [Kadavu musk parrot, foundOnIsland, Kadavu]
-
A.
Kadavu
chosen
Kadavu is one of Fiji's main islands, known for its rugged, unspoiled landscapes and world-class diving along the Great Astrolabe Reef.
-
B.
Tinakula
Tinakula is an active volcanic island in the Solomon Islands’ Santa Cruz group, known for its steep cone rising dramatically from the sea and frequent eruptions.
-
C.
Gavutu
Gavutu is a small island in the Central Province of the Solomon Islands, historically notable as a strategic site during World War II.
-
D.
Cakaudrove
Cakaudrove is a province in Fiji located on the island of Vanua Levu, known for its traditional chiefly system and rich cultural heritage.
-
E.
Tanna
Tanna is a volcanic island in southern Vanuatu known for its active Mount Yasur volcano and traditional kastom villages.
- 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_69d8278a06e481908b5d6af0a8afe737 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6210213481908fac6893e8a9f143 |
completed | April 14, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4676a2bc8190af239516ddbbf5e3 |
completed | May 8, 2026, 2:12 a.m. |
Created at: April 10, 2026, 1:06 a.m.