Triple
T37253024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | N-35 National Highway |
E924043
|
entity |
| Predicate | terminusLocationNorth |
P3375
|
FINISHED |
| Object | Khunjerab Pass |
—
|
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: Khunjerab Pass | Statement: [N-35 National Highway, terminusLocationNorth, Khunjerab Pass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terminusLocationNorth Context triple: [N-35 National Highway, terminusLocationNorth, Khunjerab Pass]
-
A.
terminusNorth
chosen
Indicates that one entity serves as the northern endpoint or final stop of another entity, such as a route, line, or path.
-
B.
terminusNortheast
Indicates that one entity serves as the northeastern terminus or endpoint of another entity (such as a route, line, or path).
-
C.
terminusLocatedOn
Indicates that the endpoint or final stop of one entity (such as a route or line) is situated on or at another entity (such as a street, line, or location).
-
D.
terminusBLocation
Indicates the location at which the B end or second endpoint of something (such as a route, connection, or segment) is situated.
-
E.
terminusSouthNear
Indicates that the southern end or terminus of one entity is located close to another entity.
- 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_69f76eaabb4c819093b751b139dad551 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:15 p.m.