Triple

T8971873
Position Surface form Disambiguated ID Type / Status
Subject College Green E214284 entity
Predicate connectsRoad P11435 FINISHED
Object Grafton Street E770259 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: Grafton Street | Statement: [College Green, connectsRoad, Grafton Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grafton Street
Context triple: [College Green, connectsRoad, Grafton Street]
  • A. Grafton Street chosen
    Grafton Street is one of Dublin’s main pedestrian shopping streets, famous for its high-end stores, street performers, and vibrant atmosphere.
  • B. O’Connell Street
    O’Connell Street is Dublin’s main thoroughfare and a historic central boulevard known for its monuments, shops, and role in Ireland’s political and social life.
  • C. Kildare Street
    Kildare Street is a prominent street in central Dublin, Ireland, known for housing key national institutions, including the Irish parliament at Leinster House.
  • D. Parnell Street
    Parnell Street is a major thoroughfare in central Dublin, Ireland, known for its mix of retail, entertainment venues, and diverse international restaurants.
  • E. Hennessy Street
    Hennessy Street is a New York-style backlot set on the Warner Bros. studio lot frequently used for filming urban street scenes in movies and television shows.
  • 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.