Triple
T7768080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King’s Cross St Pancras Underground station |
E178999
|
entity |
| Predicate | hasInterchangeTunnels |
P21069
|
FINISHED |
| Object | subterranean pedestrian tunnels |
—
|
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: subterranean pedestrian tunnels | Statement: [King’s Cross St Pancras Underground station, hasInterchangeTunnels, subterranean pedestrian tunnels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInterchangeTunnels Context triple: [King’s Cross St Pancras Underground station, hasInterchangeTunnels, subterranean pedestrian tunnels]
-
A.
hasTunnel
chosen
Indicates that one entity possesses, contains, or is connected by a tunnel to another entity.
-
B.
hasInterchangesWith
Indicates that two transportation routes, lines, or services share one or more points where passengers can transfer between them.
-
C.
hasTunnelsOnRoad
Indicates that a road includes or passes through one or more tunnels along its route.
-
D.
usesTunnel
Indicates that one entity makes use of a tunnel as a passage or route to reach or connect to another entity.
-
E.
hasTunnelShape
Indicates that something possesses a form or configuration resembling a tunnel, typically elongated, enclosed, and passage-like.
- 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_69c69f30602c819082ab52cd4af5c592 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c70435b7f88190a5e68e6ae701c58f |
completed | March 27, 2026, 10:27 p.m. |
| PD | Predicate disambiguation | batch_69c7016f4ce881909c2e9f610255187b |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:11 p.m.