Triple
T12696117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salang Tunnel |
E303337
|
entity |
| Predicate | shortenedDistanceBetween |
P12934
|
FINISHED |
| Object | Kabul and northern Afghanistan |
—
|
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: Kabul and northern Afghanistan | Statement: [Salang Tunnel, shortenedDistanceBetween, Kabul and northern Afghanistan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shortenedDistanceBetween Context triple: [Salang Tunnel, shortenedDistanceBetween, Kabul and northern Afghanistan]
-
A.
significantlyShortensRouteBetween
chosen
Indicates that one entity provides a connection between two others that makes the path or travel distance between them substantially shorter than alternative routes.
-
B.
shortestNear
Indicates that one entity is the closest (or among the closest) to another entity compared to other nearby alternatives.
-
C.
distancedFrom
Indicates that one entity is physically or metaphorically kept at a certain distance or separation from another entity.
-
D.
approximateRouteLength
Indicates the estimated total distance or length of a given route, rather than its exact measured value.
-
E.
distanceProvidedBy
Indicates that a specific distance value is supplied or made available by a particular source or provider.
- 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_69d7bdef90d48190b46b88270e780946 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d962a32c6481908ddaddae4ea267bf |
completed | April 10, 2026, 8:50 p.m. |
| PD | Predicate disambiguation | batch_69d960be63f081908a5ef5ef17a311bf |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:22 p.m.