Triple
T4947505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boyle |
E111086
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Boylan |
E466757
|
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: Boylan | Statement: [Boyle, hasVariant, Boylan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boylan Context triple: [Boyle, hasVariant, Boylan]
-
A.
Boylan
chosen
Boylan is the surname of Blazes Boylan, a character in James Joyce’s novel "Ulysses."
-
B.
Boyer
Boyer is a surname most notably associated with Herbert Boyer, a pioneering biochemist and co-founder of the biotechnology company Genentech.
-
C.
Blazes Boylan
Blazes Boylan is a charismatic and womanizing Dublin music promoter best known as Molly Bloom’s lover in James Joyce’s novel "Ulysses."
-
D.
Boyd
Boyd is a surname of Scottish origin commonly borne by individuals and families in English-speaking countries.
-
E.
Boyd Langton
Boyd Langton is a central character in the TV series "Dollhouse," serving as a morally conflicted handler and protector within the secretive organization that runs the Dollhouse.
- 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_69bd441721cc819085c7e33fe0876818 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd70abf8dc819090269d0e1ce9f871 |
completed | March 20, 2026, 4:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be77c873dc81909129644cf929ed5e |
completed | March 21, 2026, 10:49 a.m. |
Created at: March 20, 2026, 1:31 p.m.