Triple
T27023603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pahonyothin Road |
E680728
|
entity |
| Predicate | northernTerminusLocatedIn |
P51970
|
FINISHED |
| Object | Chiang Rai Province |
—
|
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: Chiang Rai Province | Statement: [Pahonyothin Road, northernTerminusLocatedIn, Chiang Rai Province]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: northernTerminusLocatedIn Context triple: [Pahonyothin Road, northernTerminusLocatedIn, Chiang Rai Province]
-
A.
northernTerminusConnects
Indicates that a route, line, or pathway connects to or ends at a specified location at its northernmost terminus.
-
B.
northernTerminusCity
Indicates that one city serves as the northern endpoint or final stop of a route, line, or corridor relative to another location.
-
C.
northernTerminusNearbyPlace
Indicates that a place serves as, or is located very close to, the northern endpoint of a route, line, or similar feature.
-
D.
northernTerminusRegion
chosen
Indicates that a location or route has its northern endpoint or final stopping point within a specified region.
-
E.
northernTerminusMunicipality
Indicates that a municipality serves as the northern endpoint or terminus of a route, line, or similar linear feature.
- 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_69eeeb5450988190bfc9a3c012ac463a |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6222ec35c819086b41052677212e1 |
completed | May 2, 2026, 4:11 p.m. |
| PD | Predicate disambiguation | batch_69f620e0b37481909a280574decbd443 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 7:09 a.m.