Triple
T19858516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Banville |
E477197
|
entity |
| Predicate | writesUnderNameFor |
P123159
|
FINISHED |
| Object | Benjamin Black, crime novels |
—
|
LITERAL 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: Benjamin Black, crime novels | Statement: [John Banville, writesUnderNameFor, Benjamin Black, crime novels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: writesUnderNameFor Context triple: [John Banville, writesUnderNameFor, Benjamin Black, crime novels]
-
A.
writesAs
Indicates that an entity creates written content under a particular name, style, or persona.
-
B.
writesTo
Indicates that one entity produces and records information, data, or content into another entity as a destination or storage target.
-
C.
writtenUnderHeteronym
chosen
Indicates that a work was written by an author using a specific heteronym (an alternate literary persona distinct from their primary identity).
-
D.
nameWrittenIn
Indicates that an entity’s name is written or recorded using a specified language, script, or writing system.
-
E.
writesForLevel
Indicates that an agent creates written content intended for a specific level, such as a grade, proficiency, or difficulty tier.
- F. None of above.
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_69d8e51e7d948190aedbcd6c30361c39 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6586dbbf0819089e7157d416aeaaf |
completed | April 20, 2026, 4:46 p.m. |
| PD | Predicate disambiguation | batch_69e537e21d2881909b1be82f02b99d40 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:51 p.m.