Triple
T30724895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Padang Besar, Thailand |
E782250
|
entity |
| Predicate | borderTownTwin |
P107933
|
FINISHED |
| Object | Padang Besar, Perlis |
—
|
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: Padang Besar, Perlis | Statement: [Padang Besar, Thailand, borderTownTwin, Padang Besar, Perlis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderTownTwin Context triple: [Padang Besar, Thailand, borderTownTwin, Padang Besar, Perlis]
-
A.
isBorderTownBetween
Indicates that a town is located on or near the boundary separating two specified regions, serving as a border settlement between them.
-
B.
borderTownAccess
Indicates that an entity has permission or the ability to enter, use, or pass through a town located on or near a border.
-
C.
oppositeTownAcrossBorder
Indicates that one town is located directly across a border from another town, positioned as its opposite counterpart.
-
D.
borderTownAcrossBorder
chosen
Indicates that a town lies on one side of a border directly opposite or adjacent to a town on the other side of that border.
-
E.
borderTownOnFrenchSide
Indicates that a town is located on the French side of a border shared with another country.
- F. None of above.
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_69f224ad9f9c81908e02a79ae0001137 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe8f74748c8190bd14a856c057f9f7 |
completed | May 9, 2026, 1:35 a.m. |
| PD | Predicate disambiguation | batch_69fe8e7ed8088190929e0df67aca4de9 |
completed | May 9, 2026, 1:31 a.m. |
Created at: April 29, 2026, 8:36 p.m.