Triple
T2271628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London Waterloo railway station |
E50670
|
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: [London Waterloo railway station, near, London Eye]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: London Eye Context triple: [London Waterloo railway station, 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.
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.
-
E.
BT Tower
BT Tower is a prominent telecommunications tower and London landmark known for its distinctive cylindrical shape and role in broadcasting and communications.
- 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_69a88b05910c8190a9a2b1ff230c85f9 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc1c0de488190876b644cdaa41637 |
completed | March 7, 2026, 6:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae71db927c8190a76cfb873039b04b |
completed | March 9, 2026, 7:08 a.m. |
Created at: March 4, 2026, 7:48 p.m.