Triple
T18832843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bandung–Banjar railway |
E460577
|
entity |
| Predicate | terminus |
P388
|
FINISHED |
| Object | Bandung Station |
—
|
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: Bandung Station | Statement: [Bandung–Banjar railway, terminus, Bandung Station]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bandung Station Context triple: [Bandung–Banjar railway, terminus, Bandung Station]
-
A.
Bandung railway station
chosen
Bandung railway station is the main rail hub in Bandung, Indonesia, serving as a key junction for intercity and regional train services across West Java and beyond.
-
B.
Bogor Station
Bogor Station is a major railway station and commuter rail terminus serving the city of Bogor and the greater Jakarta metropolitan area in Indonesia.
-
C.
Bojong Gede Station
Bojong Gede Station is a commuter rail station serving the Bojong Gede area in the Greater Jakarta region of Indonesia.
-
D.
Garut Station
Garut Station is a railway station in Garut, West Java, Indonesia, serving as a key terminus for regional passenger services on the Bandung–Garut line.
-
E.
Bekasi Station
Bekasi Station is a major railway station serving commuter and intercity trains in the city of Bekasi, Indonesia.
- 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a99b540c8190a29e5f9d56791d41 |
completed | April 20, 2026, 4:20 a.m. |
Created at: April 10, 2026, 11:56 a.m.