Triple

T19375178
Position Surface form Disambiguated ID Type / Status
Subject Tower E484647 entity
Predicate adjacentTo P224 FINISHED
Object Tower Bridge 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: Tower Bridge | Statement: [Tower, adjacentTo, Tower Bridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tower Bridge
Context triple: [Tower, adjacentTo, Tower Bridge]
  • A. Tower Bridge chosen
    Tower Bridge is a combined bascule and suspension bridge over the River Thames in London, renowned for its twin Gothic-style towers and status as one of the city's most famous landmarks.
  • B. Tower Bridge
    Tower Bridge is an iconic yellow-gold vertical-lift bridge spanning the Sacramento River, connecting West Sacramento to downtown Sacramento in California.
  • C. Westminster Bridge
    Westminster Bridge is a historic road and foot traffic bridge in central London that spans the River Thames between Westminster and Lambeth, adjacent to landmarks like the Houses of Parliament and Big Ben.
  • D. Battersea Bridge
    Battersea Bridge is a road and foot traffic bridge over the River Thames in London, connecting the districts of Battersea and Chelsea.
  • E. King’s College Bridge
    King’s College Bridge is a historic stone footbridge over the River Cam in Cambridge, England, linking the grounds of King’s College and forming part of the city’s famous riverside views.
  • 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_69d8e8d460d88190abf0591c5c9d2b0c completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e61a5acc4481908fecfb57af16d037 completed April 20, 2026, 12:21 p.m.
Created at: April 10, 2026, 1:35 p.m.