Triple
T13864624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sangirese people |
E333288
|
entity |
| Predicate | culturalRegion |
P1968
|
FINISHED |
| Object | East Indonesia |
E131540
|
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: East Indonesia | Statement: [Sangirese people, culturalRegion, East Indonesia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: East Indonesia Context triple: [Sangirese people, culturalRegion, East Indonesia]
-
A.
eastern Indonesia
chosen
Eastern Indonesia is a broad geographic region of Indonesia encompassing the country’s eastern islands, known for its cultural diversity, rich marine biodiversity, and relatively less-developed infrastructure compared to western Indonesia.
-
B.
northern Indonesia
Northern Indonesia is the geographically diverse, largely maritime region at the top of the Indonesian archipelago, encompassing island groups near the Philippines and the Celebes Sea.
-
C.
Central Indonesia
Central Indonesia is a broad geographical area of the Indonesian archipelago that includes parts of Sulawesi and surrounding islands, known for its linguistic diversity and numerous indigenous language families.
-
D.
western Indonesia
Western Indonesia is the region of Indonesia that lies closest to mainland Southeast Asia, including major areas such as Sumatra, Java, and parts of Borneo.
-
E.
Indonesian Indian Ocean coast
The Indonesian Indian Ocean coast is the stretch of shoreline along Indonesia’s southern and western islands where the country meets the Indian Ocean, known for its tectonic activity, rich marine biodiversity, and significant fishing and shipping routes.
- 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_69d81c5ced9c8190b0e9bcc6effe5959 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de05c30d9c81908217d41a3b4aaf85 |
completed | April 14, 2026, 9:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c70c41f081908b6af3f419d8468d |
completed | May 3, 2026, 10:07 p.m. |
Created at: April 9, 2026, 10:14 p.m.