Triple

T10768072
Position Surface form Disambiguated ID Type / Status
Subject Liffey Street E254003 entity
Predicate connectsTo P845 FINISHED
Object Abbey Street E899175 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: Abbey Street | Statement: [Liffey Street, connectsTo, Abbey Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Abbey Street
Context triple: [Liffey Street, connectsTo, Abbey Street]
  • A. Abbey Street chosen
    Abbey Street is a central Luas tram stop in Dublin, Ireland, serving the city’s main shopping and commercial district.
  • B. Donegall Street
    Donegall Street is a historic street in central Belfast, Northern Ireland, known for its notable architecture, cultural landmarks, and proximity to key civic and religious buildings.
  • 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. Dolores Street
    Dolores Street is a prominent north–south thoroughfare in San Francisco’s Mission District, known for its historic homes, palm-lined median, and proximity to Mission Dolores Park.
  • E. Pearse Street
    Pearse Street is a major thoroughfare in central Dublin, Ireland, known for its mix of cultural institutions, educational buildings, and historic city architecture.
  • 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_69d6aa5f54f4819082d0bbcb6f8797e6 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d7322f9968819098b0ad54b913bfe4 completed April 9, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69e3e6d27d8c8190b2c8ee9c54cf7fd1 completed April 18, 2026, 8:17 p.m.
Created at: April 8, 2026, 9:16 p.m.