Triple
T11995484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Thewlis as Paul Verlaine |
E285517
|
entity |
| Predicate | basedOnOccupation |
P2374
|
FINISHED |
| Object | French poet |
—
|
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: French poet | Statement: [David Thewlis as Paul Verlaine, basedOnOccupation, French poet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedOnOccupation Context triple: [David Thewlis as Paul Verlaine, basedOnOccupation, French poet]
-
A.
basedOnProfession
Indicates that the relationship or action is determined or derived from a person’s profession or occupational role.
-
B.
basedOnCareerOf
Indicates that something (such as a work, character, or storyline) is derived from, inspired by, or modeled on the career or professional life of a particular person.
-
C.
usedByOccupation
Indicates that something (such as a tool, method, or resource) is utilized in the performance of a particular occupation or job.
-
D.
subjectOccupation
chosen
Indicates that the subject holds or performs a particular job, profession, or role as their occupation.
-
E.
dedicatedToOccupation
Indicates that an entity is committed or devoted to performing or pursuing a particular occupation or professional role.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903b211688190bfe6dd15c3f96d2f |
completed | April 10, 2026, 2:05 p.m. |
| PD | Predicate disambiguation | batch_69d902abca70819098291aa51b593708 |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:46 p.m.