Triple
T25543216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bank station |
E640225
|
entity |
| Predicate | dlrBranch |
P102299
|
FINISHED |
| Object | Bank branch of Docklands Light Railway |
—
|
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: Bank branch of Docklands Light Railway | Statement: [Bank station, dlrBranch, Bank branch of Docklands Light Railway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dlrBranch Context triple: [Bank station, dlrBranch, Bank branch of Docklands Light Railway]
-
A.
hasDLRBranch
chosen
Indicates that an entity possesses or is associated with a specific DLR (Docklands Light Railway) branch.
-
B.
branchLine
Indicates a relationship where one line, route, or path diverges from and is subordinate to a main or primary line.
-
C.
addressedBranch
Indicates that an action, communication, or item is specifically directed to or associated with a particular branch of an organization or network.
-
D.
trainedBranch
Indicates that one entity has provided training or instruction to a specific branch or subdivision of another entity.
-
E.
definesBranch
Indicates that one entity specifies or establishes a particular branch or subdivision of another entity.
- 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_69e75dbfff7081909b0aa779d48321d2 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f895e458819081cf031b70d20e56 |
completed | May 2, 2026, 1:13 p.m. |
| PD | Predicate disambiguation | batch_69f468421ba08190880eac99135e5970 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 3:27 p.m.