Triple
T22628330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laos border |
E558482
|
entity |
| Predicate | landBorderLengthWithMyanmar_km |
P57957
|
FINISHED |
| Object | about 238 |
—
|
LITERAL 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: about 238 | Statement: [Laos border, landBorderLengthWithMyanmar_km, about 238]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: landBorderLengthWithMyanmar_km Context triple: [Laos border, landBorderLengthWithMyanmar_km, about 238]
-
A.
hasInternationalBoundaryLengthWithMyanmar
Indicates the measured length of the international land or maritime boundary shared between a given entity and Myanmar.
-
B.
hasBorderTownOnMyanmarSide
Indicates that a town is located on the Myanmar side of a border shared with another country.
-
C.
shareLandBorderLengthApproxKm
chosen
Indicates that two entities share a land border whose length is approximately the given number of kilometers.
-
D.
hasInternationalBorderLengthWithBangladeshKilometres
Indicates the length, in kilometers, of the international land border shared between an entity and Bangladesh.
-
E.
hasInternationalBoundaryLengthWithBhutan
Indicates the measured length of the international land border shared between a given entity and Bhutan.
- 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_69e245467d9881908d6985bd0db7a1f1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f16e3ed1d48190a093013d829901b9 |
completed | April 29, 2026, 2:34 a.m. |
| PD | Predicate disambiguation | batch_69ee62855558819080da946c7b35a160 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 17, 2026, 3:02 p.m.