Triple

T19069640
Position Surface form Disambiguated ID Type / Status
Subject Blazes E466758 entity
Predicate fullName P16 FINISHED
Object Hugh Boylan NE NERFINISHED

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: Hugh Boylan | Statement: [Blazes, fullName, Hugh Boylan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hugh Boylan
Context triple: [Blazes, fullName, Hugh Boylan]
  • A. Hugh Boylan chosen
    Hugh Boylan, better known as Blazes Boylan, is a charismatic and flirtatious advertising agent in James Joyce’s novel "Ulysses," notable for his affair with Molly Bloom.
  • B. Gerard Horan
    Gerard Horan is a British actor known for his work in television, film, and theatre, often appearing in UK dramas and comedies.
  • C. David Nelligan
    David Nelligan was the father of renowned French-Canadian poet Émile Nelligan and a key figure in the poet’s family background.
  • D. Patrick Gleeson
    Patrick Gleeson is an American electronic music composer and synthesizer pioneer known for his film scores and collaborations in jazz and experimental music.
  • E. Michael Dinneen
    Michael Dinneen is a computer scientist known for his work in algorithms, combinatorics, and theoretical computer science.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd04f4488190b1121cc53ef2bfd6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e19caa708190876a2cb06aa0c9cc completed April 20, 2026, 8:19 a.m.
Created at: April 10, 2026, 12:03 p.m.