Triple
T20420401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Bangka Regency |
E500831
|
entity |
| Predicate | containsSettlement |
P847
|
FINISHED |
| Object | Toboali |
—
|
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: Toboali | Statement: [South Bangka Regency, containsSettlement, Toboali]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Toboali Context triple: [South Bangka Regency, containsSettlement, Toboali]
-
A.
Toboali
chosen
Toboali is a coastal town and administrative center in the southern part of Bangka Island in Indonesia, known historically for its tin mining activities.
-
B.
Dobuan
Dobuan is an Austronesian language spoken on Dobu Island and nearby areas in Papua New Guinea.
-
C.
Belawa
Belawa is a town and administrative district located within Wajo Regency in South Sulawesi, Indonesia.
-
D.
Bambarra
Bambarra is a small coastal village on Middle Caicos in the Turks and Caicos Islands, known for its historical links to African heritage and its tranquil, undeveloped beaches.
-
E.
Labis
Labis is a small town in the Segamat District of Johor, Malaysia, known as a local commercial and agricultural hub.
- 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_69e0b4aa68fc8190b1a14c55575ef04a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67ba39f7081909358f1103a0f241c |
completed | April 20, 2026, 7:16 p.m. |
Created at: April 16, 2026, 11:30 a.m.