Triple
T12163656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beckton station |
E289773
|
entity |
| Predicate | hasCanaryWharfConnection |
P61380
|
FINISHED |
| Object | via DLR |
—
|
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: via DLR | Statement: [Beckton station, hasCanaryWharfConnection, via DLR]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCanaryWharfConnection Context triple: [Beckton station, hasCanaryWharfConnection, via DLR]
-
A.
hasCanaryWharfComplexConnection
chosen
Indicates a relationship where one entity is connected or related to the Canary Wharf complex, such as through location, infrastructure, or direct association.
-
B.
hasCausewayConnection
Indicates a relationship where two locations are physically linked by a causeway, allowing passage between them.
-
C.
positionRelativeToCanaryWharf
Indicates the spatial or locational relationship of an entity with respect to Canary Wharf.
-
D.
connectsViaCanal
Indicates that one entity is linked or joined to another by means of a canal.
-
E.
hasUndergroundConnections
Indicates that one entity is linked to another through subterranean or hidden passageways, networks, or channels.
- 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_69d6ab4d6c00819095a9a7c35de83cfb |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915d7109481908bf5fe512bba3c89 |
completed | April 10, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69d9150c18148190bf8152189c0e5fca |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:50 p.m.