Triple
T18473486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malé Island |
E451363
|
entity |
| Predicate | primaryLanguage |
P238
|
FINISHED |
| Object | Dhivehi |
—
|
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: Dhivehi | Statement: [Malé Island, primaryLanguage, Dhivehi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dhivehi Context triple: [Malé Island, primaryLanguage, Dhivehi]
-
A.
Dhivehi
chosen
Dhivehi is an Indo-Aryan language spoken primarily in the Maldives, where it serves as the national language of the Maldivian people.
-
B.
Dhives Akuru
Dhives Akuru is an ancient script formerly used to write the Maldivian Dhivehi language before its replacement by the modern Thaana script.
-
C.
Maldives
The Maldives is a tropical island nation in the Indian Ocean renowned for its white-sand beaches, coral reefs, and luxury overwater resorts.
-
D.
Kurumba Maldives
Kurumba Maldives is a luxury island resort in the Maldives known for its white-sand beaches, overwater experiences, and upscale tropical accommodations.
-
E.
Mohéli
Mohéli is the smallest and least populated of the three main islands of the Union of the Comoros, known for its rich marine biodiversity and relatively unspoiled natural 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_69d8d38465a0819099b9b42d2a662ac1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e530617e48819091240d4405e53aaa |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 11:34 a.m.