Triple
T30259559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London King’s Cross–Leeds |
E769448
|
entity |
| Predicate | hasDirectConnectionBetween |
P845
|
FINISHED |
| Object | central London |
—
|
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: central London | Statement: [London King’s Cross–Leeds, hasDirectConnectionBetween, central London]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDirectConnectionBetween Context triple: [London King’s Cross–Leeds, hasDirectConnectionBetween, central London]
-
A.
isDirectConnection
Indicates that there is an immediate, unmediated link or relationship between two entities without any intermediate steps or nodes.
-
B.
connectedByStraitTo
Indicates that one entity is geographically linked to another by a narrow body of water known as a strait.
-
C.
connectsTo
chosen
Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
-
D.
isOnlyDirectTransitLinkBetween
Indicates that this connection is the single, exclusive direct transit route linking the two entities, with no alternative direct transit links between them.
-
E.
indirectlyConnects
Indicates that one entity is connected to another through one or more intermediate entities or links, rather than by a direct connection.
- 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_69f22484a5f48190b678cd607700bc82 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd5f29b1988190877764ef2a399c7f |
completed | May 8, 2026, 3:57 a.m. |
| PD | Predicate disambiguation | batch_69fd5e30194c819085b5ce586122ab37 |
completed | May 8, 2026, 3:53 a.m. |
Created at: April 29, 2026, 7:41 p.m.