Triple
T20471945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quirke |
E502214
|
entity |
| Predicate | authorOfSourceMaterial |
P2806
|
FINISHED |
| Object | Benjamin Black |
—
|
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: Benjamin Black | Statement: [Quirke, authorOfSourceMaterial, Benjamin Black]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Benjamin Black Context triple: [Quirke, authorOfSourceMaterial, Benjamin Black]
-
A.
Benjamin Black
chosen
Benjamin Black is the crime-writing pseudonym of Irish novelist John Banville, under which he publishes noir-inflected mystery fiction.
-
B.
Stephen Donoghue
Stephen Donoghue is a literary critic and book reviewer known for his prolific online reviews and commentary on contemporary and classic literature.
-
C.
John Connolly
John Connolly was a real-life FBI agent in Boston notorious for his corrupt relationship with mobster Whitey Bulger, a story dramatized in the film "Black Mass."
-
D.
John Connolly
John Connolly is an Irish author best known for his crime fiction series featuring private detective Charlie Parker.
-
E.
Dermot Povey
Dermot Povey is a fictional character from the British sitcom "Men Behaving Badly," known as one of the show's central male leads.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6996197908190b6570e2a7fd6cf67 |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:33 a.m.