Triple
T1642864
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tower Bridge |
E35511
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Southwark |
E20778
|
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: Southwark | Statement: [Tower Bridge, connects, Southwark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Southwark Context triple: [Tower Bridge, connects, Southwark]
-
A.
Southwark
chosen
Southwark is a historic district in central London on the south bank of the River Thames, known for landmarks such as Borough Market, The Shard, and Shakespeare’s Globe.
-
B.
Lambeth
Lambeth is a central London borough on the south bank of the River Thames, known for landmarks such as the London Eye and its diverse urban communities.
-
C.
Bermondsey
Bermondsey is a district in southeast London known for its riverside location along the Thames, regenerated warehouse areas, and vibrant food and arts scene.
-
D.
Hammersmith
Hammersmith is a district in West London known as a major commercial and transport hub along the River Thames.
-
E.
Wandsworth
Wandsworth is a district in southwest London, England, known for its riverside location on the River Thames and its mix of residential, commercial, and green spaces.
- 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_69a88604618c81908b41f6429c431eb6 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90a3f4d8c8190aa0a44d1c9b1a7f0 |
completed | March 5, 2026, 4:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aebef5ac7c81908015969c04fcc425 |
completed | March 9, 2026, 12:37 p.m. |
Created at: March 4, 2026, 7:28 p.m.