Triple
T20489956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windsor Bridge |
E502713
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Eton College |
—
|
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: Eton College | Statement: [Windsor Bridge, near, Eton College]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eton College Context triple: [Windsor Bridge, near, Eton College]
-
A.
Eton College
chosen
Eton College is a prestigious independent boarding school for boys in England, renowned for educating numerous British prime ministers and other prominent figures.
-
B.
Eton School
Eton School is a private educational institution in Santa Fe, Mexico City, known for offering bilingual, internationally oriented schooling.
-
C.
Eton
Eton is a Bantu language spoken by the Beti-Pahuin people, primarily in central Cameroon.
-
D.
Eton
Eton is a small city in Murray County, Georgia, known for its rural character and proximity to the Appalachian foothills.
-
E.
Wellington College
Wellington College is a prestigious English public boarding school in Berkshire, known for its strong academic tradition and historic military associations.
- 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_69e0b4b0373881909dd3e9387f82eab4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69b5d93ec81908259696359090b35 |
completed | April 20, 2026, 9:32 p.m. |
Created at: April 16, 2026, 11:34 a.m.