Triple
T21298144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marion Bloom |
E524981
|
entity |
| Predicate | hasAffairWith |
P23617
|
FINISHED |
| Object | Blazes 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: Blazes Boylan | Statement: [Marion Bloom, hasAffairWith, Blazes Boylan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blazes Boylan Context triple: [Marion Bloom, hasAffairWith, Blazes Boylan]
-
A.
Blazes Boylan
chosen
Blazes Boylan is a charismatic and womanizing Dublin music promoter best known as Molly Bloom’s lover in James Joyce’s novel "Ulysses."
-
B.
John Boylan
John Boylan is a Canadian actor known for his extensive work in film and television, including roles in series like Being Erica and films such as The Story of Luke.
-
C.
John Boylan
John Boylan is an American record producer best known for his work with artists such as Boston, Linda Ronstadt, and the Eagles.
-
D.
Hugh "Blazes" Boylan
Hugh "Blazes" Boylan is a charismatic advertising canvasser and womanizer in James Joyce's novel "Ulysses," best known as the lover of Molly Bloom.
-
E.
Darin Gray
Darin Gray is an American bassist and experimental musician known for his work in avant-garde, improvisational, and indie rock projects and collaborations.
- 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_69e0b517e6748190850d6f6ddf323d69 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7385a24d08190bfd410c7f10fa6f7 |
completed | April 21, 2026, 8:42 a.m. |
Created at: April 16, 2026, 4:04 p.m.