Triple
T11508547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London Wall |
E272848
|
entity |
| Predicate | hadGate |
P4365
|
FINISHED |
| Object | Bishopsgate |
E161437
|
NE 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: Bishopsgate | Statement: [London Wall, hadGate, Bishopsgate]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bishopsgate Context triple: [London Wall, hadGate, Bishopsgate]
-
A.
Bishopsgate
chosen
Bishopsgate is a historic street and district in the City of London known for its mix of financial institutions, modern skyscrapers, and preserved medieval and Victorian architecture.
-
B.
22 Bishopsgate
22 Bishopsgate is a prominent skyscraper in the City of London, known for being one of the tallest buildings in the United Kingdom and a major commercial office hub.
-
C.
Aldgate
Aldgate is a small township in the Adelaide Hills region of South Australia, known for its leafy surroundings and village-style atmosphere.
-
D.
Aldgate
Aldgate is a central London Underground station in the City of London, serving as a key interchange and endpoint for multiple Tube lines.
-
E.
Leadenhall Building
The Leadenhall Building is a distinctive, tapering skyscraper in the City of London, popularly nicknamed "The Cheesegrater" for its unique wedge-shaped profile.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aae2c3748190bed2ea50dfb160dc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d86db43a648190be859bec2fe9f43b |
completed | April 10, 2026, 3:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e6852a23688190a3fe8e5508435661 |
completed | April 20, 2026, 7:57 p.m. |
Created at: April 8, 2026, 9:36 p.m.