Triple
T24154073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joseph Eybler |
E598625
|
entity |
| Predicate | assistedOnWorkOf |
P104801
|
FINISHED |
| Object | Wolfgang Amadeus Mozart |
—
|
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: Wolfgang Amadeus Mozart | Statement: [Joseph Eybler, assistedOnWorkOf, Wolfgang Amadeus Mozart]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: assistedOnWorkOf Context triple: [Joseph Eybler, assistedOnWorkOf, Wolfgang Amadeus Mozart]
-
A.
supportingWork
Indicates that one work provides assistance, reinforcement, or supplementary value to another work, helping to sustain or enhance it.
-
B.
wasAssistedBy
Indicates that an entity carried out an action or achieved a result with the help or support of another entity.
-
C.
contributionToWork
chosen
Indicates a relationship where an entity has provided effort, input, or resources that help create, develop, or complete a particular work.
-
D.
associatedWithWorkOf
Indicates that one entity has a connection or involvement with the work, creation, or output produced by another entity.
-
E.
associatedWork
Indicates that there exists a related or connected work (such as a publication, creative piece, or project) that is meaningfully linked to the subject.
- 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_69e288cb0a3081909ef221744f274384 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1e0e2e83081908e543ef266a27ec9 |
completed | April 29, 2026, 10:43 a.m. |
| PD | Predicate disambiguation | batch_69f176585f3481909beb907de252cd98 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:31 p.m.