Triple
T8456998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London–Lille |
E199942
|
entity |
| Predicate | openedViaChannelTunnel |
P51762
|
FINISHED |
| Object | 1994 |
—
|
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: 1994 | Statement: [London–Lille, openedViaChannelTunnel, 1994]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openedViaChannelTunnel Context triple: [London–Lille, openedViaChannelTunnel, 1994]
-
A.
openedTunnelReplacementFor
Indicates that one tunnel has been opened specifically to serve as a replacement for another tunnel.
-
B.
tunnelOpened
chosen
Indicates that a tunnel has been created or made accessible, establishing an open passage between two locations or systems.
-
C.
hasTunnel
Indicates that one entity possesses, contains, or is connected by a tunnel to another entity.
-
D.
openedRouteThrough
Indicates that one entity has created or established a passage, connection, or pathway that allows movement or access through another entity or area.
-
E.
secondTunnelOpened
Indicates that a second tunnel has been opened and is now available for use in addition to an existing tunnel.
- 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_69ca8318231881908fd1bc1c4d45d286 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe48f180c8190a71cf9d7248ade60 |
completed | March 31, 2026, 3:13 p.m. |
| PD | Predicate disambiguation | batch_69cbd0fc634481909842c0a30077bfde |
completed | March 31, 2026, 1:49 p.m. |
Created at: March 30, 2026, 6:10 p.m.