Triple
T18000070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince's Street |
E430604
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Bank junction |
—
|
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 junction | Statement: [Prince's Street, near, Bank junction]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bank junction Context triple: [Prince's Street, near, Bank junction]
-
A.
Bank junction
chosen
Bank junction is a major road intersection and financial hub in the City of London, surrounded by landmark institutions such as the Bank of England and the Royal Exchange.
-
B.
Banking Bureau
The Banking Bureau is a regulatory authority in Taiwan responsible for overseeing and supervising the banking sector under the Financial Supervisory Commission.
-
C.
Bank
Bank is a major London Underground and rail interchange in the City of London, serving as a key hub for financial district commuters.
-
D.
Banks
Banks is a small village in Lancashire, England, known for its rural character and proximity to the town of Tarleton.
-
E.
Banks
Banks is a residential suburb in the Tuggeranong district of Canberra, Australian Capital Territory.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b90364248190a37381adea932f42 |
completed | April 10, 2026, 8:46 a.m. |
| NER | Named-entity recognition | batch_69e4b3e75e908190a6ff6a3ec6069ff5 |
completed | April 19, 2026, 10:52 a.m. |
Created at: April 10, 2026, 10:23 a.m.