Triple

T13010904
Position Surface form Disambiguated ID Type / Status
Subject Victoria Square (Birmingham) E322405 entity
Predicate hasStreetConnection P36837 FINISHED
Object Hill Street E139997 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: Hill Street | Statement: [Victoria Square (Birmingham), hasStreetConnection, Hill Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hill Street
Context triple: [Victoria Square (Birmingham), hasStreetConnection, Hill Street]
  • A. Hill Street chosen
    Hill Street is a central street in Birmingham, England, located near and providing access to the major Birmingham New Street railway station.
  • B. Hill Street
    Hill Street is a street in the Mayfair district of central London, known for its upscale residences and proximity to Berkeley Square.
  • C. Hill Street
    Hill Street is a historic roadway located within the Cobbham Historic District, an early residential neighborhood in Athens, Georgia.
  • D. Bryant Street
    Bryant Street is a notable thoroughfare in downtown Palo Alto known for its mix of shops, restaurants, and proximity to the city’s commercial and tech hubs.
  • E. Bryant Street
    Bryant Street is a major thoroughfare in San Francisco known for connecting the South of Market and Mission District areas and serving a mix of residential, commercial, and light industrial uses.
  • 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_69d807657e8c8190bd9435ee2f823845 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e9e14b88190a2cee8e0c9bf31c8 completed April 10, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0025e6bc748190b8099e7559569a90 completed May 10, 2026, 6:29 a.m.
Created at: April 9, 2026, 8:49 p.m.