Triple
T8846097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waterloo East |
E210507
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | London Eye |
E9035
|
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: London Eye | Statement: [Waterloo East, near, London Eye]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: London Eye Context triple: [Waterloo East, near, London Eye]
-
A.
London Eye
chosen
The London Eye is a giant riverside observation wheel in central London offering panoramic views of the city’s skyline and landmarks.
-
B.
Skylon Tower
Skylon Tower is an observation tower in Niagara Falls, Ontario, known for its panoramic views of the falls and its revolving dining room.
-
C.
Seattle Great Wheel
The Seattle Great Wheel is a large Ferris wheel on Pier 57 along Seattle’s waterfront, offering panoramic views of the city skyline and Elliott Bay.
-
D.
Brighton i360
Brighton i360 is a seafront observation tower in Brighton, England, known for its glass viewing pod that offers panoramic coastal and city views.
-
E.
Tempozan Giant Ferris Wheel
Tempozan Giant Ferris Wheel is a large, popular observation wheel in Osaka, Japan, offering panoramic views of the city and Osaka Bay.
- 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_69ca838967bc8190b46c3c80a2887ea4 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60a7c518819095399976148e1b9a |
completed | April 1, 2026, 12:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf89b5acbc8190b0f5a81af71fc7aa |
completed | April 3, 2026, 9:34 a.m. |
Created at: March 30, 2026, 6:48 p.m.