Triple
T15876374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rakhine State |
E384961
|
entity |
| Predicate | hasBorderTown |
P847
|
FINISHED |
| Object | Maungdaw |
E1002410
|
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: Maungdaw | Statement: [Rakhine State, hasBorderTown, Maungdaw]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maungdaw Context triple: [Rakhine State, hasBorderTown, Maungdaw]
-
A.
Maungdaw
chosen
Maungdaw is a town in Myanmar’s Rakhine State near the border with Bangladesh, known for its ethnically diverse population and its role in regional trade and migration.
-
B.
Kawthaung
Kawthaung is a coastal town in southern Myanmar that serves as a key gateway for cross-border trade and travel with Thailand.
-
C.
Nyaungshwe
Nyaungshwe is a popular lakeside town in Myanmar that serves as the main gateway and tourist hub for visiting Inle Lake in Shan State.
-
D.
Mogaung
Mogaung is a town in northern Myanmar notable as a local administrative and transport center within Kachin State.
-
E.
Nyaung-U
Nyaung-U is a historic town in central Myanmar best known as the main gateway to the ancient temple plain of Bagan.
- 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_69d86da4e86481909f1325fdc971b5ec |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e155fdc1b881909d1c82c4c66a195a |
completed | April 16, 2026, 9:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb59ddc488190ae6b6913f85005f6 |
completed | May 9, 2026, 10:30 p.m. |
Created at: April 10, 2026, 4:51 a.m.