Triple

T8971877
Position Surface form Disambiguated ID Type / Status
Subject College Green E214284 entity
Predicate locatedNear P294 FINISHED
Object Temple Bar E254025 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: Temple Bar | Statement: [College Green, locatedNear, Temple Bar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Temple Bar
Context triple: [College Green, locatedNear, Temple Bar]
  • A. Temple Bar
    Temple Bar is a historic ceremonial gateway in London that once marked the western boundary of the City of London and the start of the Strand.
  • B. Temple Bar district chosen
    Temple Bar district is a historic and lively cultural quarter in central Dublin known for its cobbled streets, pubs, nightlife, and arts venues.
  • C. Paternoster Square
    Paternoster Square is a modern commercial and public plaza in the City of London, located near St Paul’s Cathedral and home to the London Stock Exchange.
  • D. Barbican
    Barbican is a historic area in the City of London known for its medieval fortifications and the modern Barbican Estate and arts centre complex.
  • E. Barbican
    The Barbican in Banská Bystrica is a historic fortification structure that once formed part of the town’s medieval defensive system.
  • 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_69ca839dbf608190a2f5990477115d29 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6780d45081909f2bc5295c8550f9 completed April 1, 2026, 12:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0aba020819088bc6d7a461bbcdb completed April 3, 2026, 2:37 p.m.
Created at: March 30, 2026, 7:02 p.m.