Triple
T22594949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Solor |
E574649
|
entity |
| Predicate | locatedBetween |
P1262
|
FINISHED |
| Object | Adonara |
—
|
NE NERFINISHED |
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: Adonara | Statement: [Solor, locatedBetween, Adonara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adonara Context triple: [Solor, locatedBetween, Adonara]
-
A.
Adonara Island
chosen
Adonara Island is a small volcanic island in eastern Indonesia’s Lesser Sunda Islands, known for its traditional communities and location between Flores and Lembata.
-
B.
Mahorais
Mahorais is a French-based creole language spoken primarily on the island of Mayotte in the Indian Ocean.
-
C.
Kuata Island
Kuata Island is a small tropical island in Fiji’s Yasawa archipelago, known for its rugged volcanic landscapes, clear waters, and popular snorkeling and diving spots.
-
D.
Giraavaru
Giraavaru is a small inhabited island in the Maldives, known for its traditional Maldivian community and surrounding coral reef environment.
-
E.
Hatoma Island
Hatoma Island is a small, remote island in Japan’s Yaeyama archipelago, known for its traditional Ryukyuan culture, coral reefs, and tranquil, sparsely populated environment.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245bc11308190b69d794d5d1e0bb6 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f16164d690819096f7c4efb6cedad9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 2:49 p.m.