Triple

T10328021
Position Surface form Disambiguated ID Type / Status
Subject Eton High Street E242808 entity
Predicate near P350 FINISHED
Object Windsor Bridge E502713 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: Windsor Bridge | Statement: [Eton High Street, near, Windsor Bridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Windsor Bridge
Context triple: [Eton High Street, near, Windsor Bridge]
  • A. Windsor Bridge chosen
    Windsor Bridge is a historic pedestrian and cycle bridge spanning the River Thames between the towns of Windsor and Eton in Berkshire, England.
  • B. Judith Bridge
    Judith Bridge was a medieval stone bridge in Prague that preceded and was ultimately replaced by the famous Charles Bridge after being destroyed by floods.
  • C. Elizabeth Bridge
    Elizabeth Bridge is a prominent suspension bridge spanning the Danube River in Budapest, connecting the Buda and Pest sides of the city.
  • D. Albert Bridge
    Albert Bridge is a historic road bridge in Belfast, Northern Ireland, known for carrying traffic across the River Lagan near the city centre.
  • E. Albert Bridge
    Albert Bridge is a historic and ornate road bridge over the River Thames in London, connecting Chelsea and Battersea.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d7cf21e08190bf605daeea0d9dcf completed April 7, 2026, 10:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69e154529dd08190abbfc8d8281a642f completed April 16, 2026, 9:27 p.m.
Created at: April 6, 2026, 11:51 a.m.