Triple
T22622198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arthur Gershwin |
E558311
|
entity |
| Predicate | workedPrimarilyIn |
P148956
|
FINISHED |
| Object | music publishing |
—
|
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: music publishing | Statement: [Arthur Gershwin, workedPrimarilyIn, music publishing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workedPrimarilyIn Context triple: [Arthur Gershwin, workedPrimarilyIn, music publishing]
-
A.
workedPrimarilyOn
Indicates that an entity devoted the majority of its work, effort, or activity to a particular project, field, or subject.
-
B.
workedAs
Indicates that an entity held a particular job, role, or position, performing work in that capacity.
-
C.
workAt
Indicates that an entity is employed by or performs work for a particular organization, company, or place.
-
D.
placeOfOriginOfWork
Indicates the location where a work (such as an artwork, literary piece, or other creation) was originally produced or created.
-
E.
ownsWork
Indicates that one entity has legal ownership or proprietary rights over a particular work or creation.
- F. None of above. chosen
Provenance (4 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_69e24545a8e08190bfa7482a2c725ff1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f16e3ad6f48190b351a52e4b1d9b2d |
completed | April 29, 2026, 2:34 a.m. |
| PD | Predicate disambiguation | batch_69ee62855558819080da946c7b35a160 |
completed | April 26, 2026, 7:07 p.m. |
| PDg | Predicate description generation | batch_69ee8841e9cc81908d23b34215e3be71 |
completed | April 26, 2026, 9:48 p.m. |
Created at: April 17, 2026, 3 p.m.