Triple
T32425877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pau–Canfranc railway |
E828574
|
entity |
| Predicate | borderTunnel |
P197927
|
FINISHED |
| Object | Somport Tunnel |
—
|
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: Somport Tunnel | Statement: [Pau–Canfranc railway, borderTunnel, Somport Tunnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderTunnel Context triple: [Pau–Canfranc railway, borderTunnel, Somport Tunnel]
-
A.
borderTypeAtTerminusB
Indicates the type or classification of the border present at the second (B) endpoint of a defined boundary or connection.
-
B.
borderTerminus
Indicates the endpoint location where a border between two areas or entities begins or ends.
-
C.
borderEstablished
Indicates that a formal boundary between two geographic or political entities has been officially defined and put into effect.
-
D.
borderCorridorFor
chosen
Indicates a corridor or passageway that serves as a boundary or border for another area or region.
-
E.
borderStraddling
Indicates that something (such as a feature, structure, or area) extends across and occupies territory on both sides of a border between two regions or jurisdictions.
- 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_69f3491b28bc8190b75cea7a507f337b |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ff0214d7348190904688376df99bce |
completed | May 9, 2026, 9:44 a.m. |
| PD | Predicate disambiguation | batch_69feffd62fec8190a855922c8b3c57cf |
completed | May 9, 2026, 9:35 a.m. |
Created at: May 1, 2026, 12:54 a.m.