Triple

T9097054
Position Surface form Disambiguated ID Type / Status
Subject Radcliffe Square E218051 entity
Predicate adjacentTo P224 FINISHED
Object School Street E554324 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: School Street | Statement: [Radcliffe Square, adjacentTo, School Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: School Street
Context triple: [Radcliffe Square, adjacentTo, School Street]
  • A. School Street chosen
    School Street is a historic street in downtown Boston known for its proximity to significant civic and educational landmarks.
  • B. School Lane
    School Lane is a local road in the village of Mid Calder, West Lothian, Scotland, serving residential and community areas.
  • C. Hayes High Street
    Hayes High Street is the main commercial thoroughfare and local shopping area serving the suburban district of Hayes in the London Borough of Bromley.
  • D. Hope Street
    Hope Street is a well-known thoroughfare in Liverpool, England, noted for linking the city’s two cathedrals and serving as a cultural hub with theatres, restaurants, and historic buildings.
  • E. Hope Street
    Hope Street is a major thoroughfare in downtown Los Angeles, California, running through the historic Bunker Hill area and connecting key cultural and commercial districts.
  • 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_69ca83d9844081908e561e367fda6d45 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc96b7d0d48190a3b15f35bef087e3 completed April 1, 2026, 3:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0479a58c48190acd4a4af21aa01c3 completed April 3, 2026, 11:04 p.m.
Created at: March 30, 2026, 7:15 p.m.