Triple
T27329832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trat Province |
E689764
|
entity |
| Predicate | borderCheckpointWithCambodia |
P46215
|
FINISHED |
| Object | Hat Lek Border Crossing |
—
|
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: Hat Lek Border Crossing | Statement: [Trat Province, borderCheckpointWithCambodia, Hat Lek Border Crossing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderCheckpointWithCambodia Context triple: [Trat Province, borderCheckpointWithCambodia, Hat Lek Border Crossing]
-
A.
borderStation
chosen
Indicates a facility or checkpoint located at or near a border where cross-boundary movement, control, or processing of people or goods occurs.
-
B.
borderTradePointWith
Indicates a location or facility where trade or commercial exchange occurs between two bordering regions or countries.
-
C.
borderPass
Indicates that one entity crosses or moves through the boundary separating two regions or jurisdictions.
-
D.
borderTownAcrossBorder
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.
borderStationFor
Indicates that a particular border station serves, monitors, or is responsible for a specific border crossing or boundary segment.
- 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_69ef355d4cb08190ab032c0a2e7d3753 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
Created at: April 27, 2026, 11:37 a.m.