Triple
T17419445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dharmasraya Regency |
E423572
|
entity |
| Predicate | seat |
P75
|
FINISHED |
| Object | Pulau Punjung |
—
|
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: Pulau Punjung | Statement: [Dharmasraya Regency, seat, Pulau Punjung]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pulau Punjung Context triple: [Dharmasraya Regency, seat, Pulau Punjung]
-
A.
Pulau Punjung
chosen
Pulau Punjung is a town in West Sumatra, Indonesia, serving as the administrative and governmental center of Dharmasraya Regency.
-
B.
Pulau Berbunut
Pulau Berbunut is a small river island located within Brunei’s Brunei-Muara District, known for its natural setting along the Brunei River.
-
C.
Pulau Bedukang
Pulau Bedukang is a small island located off the coast of Brunei in the Brunei-Muara District.
-
D.
Pulau Keingaran
Pulau Keingaran is a small island located within Brunei’s Brunei-Muara District, known for its coastal and marine surroundings.
-
E.
Pulau Pepatan
Pulau Pepatan is a small island located within Brunei's Brunei-Muara District, known for its coastal and village setting along the Brunei River.
- 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_69d889d7d27c819088486ce3f0627fa1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e44236419c8190a106748bca6f30cd |
completed | April 19, 2026, 2:47 a.m. |
Created at: April 10, 2026, 5:46 a.m.