Triple

T8972199
Position Surface form Disambiguated ID Type / Status
Subject Brian Boru harp E214292 entity
Predicate inspired P9 FINISHED
Object Guinness logo harp E250800 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: Guinness logo harp | Statement: [Brian Boru harp, inspired, Guinness logo harp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Guinness logo harp
Context triple: [Brian Boru harp, inspired, Guinness logo harp]
  • A. Guinness chosen
    Guinness is a world-famous Irish dry stout brand originating from Dublin and known for its dark color, creamy head, and long brewing heritage.
  • B. Arthur Guinness & Son
    Arthur Guinness & Son was the family-run brewing company behind Guinness stout, one of Ireland’s most famous and globally recognized beer brands.
  • C. Hugo Guinness
    Hugo Guinness is a British artist, illustrator, and writer known for his linocut prints and collaborations with filmmaker Wes Anderson.
  • D. Red Swoosh
    Red Swoosh was a peer-to-peer content delivery and file-sharing startup later acquired by Akamai Technologies.
  • E. Guinness Trust
    The Guinness Trust is a British charitable housing association established in the late 19th century to provide affordable homes and improve living conditions for the urban poor.
  • 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_69cfc9632afc8190a4dc14d33e8757ee completed April 3, 2026, 2:06 p.m.
Created at: March 30, 2026, 7:02 p.m.