Triple
T31629361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miyuki Shirogane |
E807118
|
entity |
| Predicate | worksHardAt |
P30363
|
FINISHED |
| Object | part-time jobs |
—
|
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: part-time jobs | Statement: [Miyuki Shirogane, worksHardAt, part-time jobs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksHardAt Context triple: [Miyuki Shirogane, worksHardAt, part-time jobs]
-
A.
worksOver
Indicates that one entity performs work that extends beyond or exceeds a certain limit, threshold, or standard associated with another entity.
-
B.
worksDuring
Indicates that an entity performs work or is on duty throughout a specified time period or schedule.
-
C.
workOn
chosen
Indicates that an agent is actively engaged in performing tasks or making progress on a particular project, object, or assignment.
-
D.
worksTo
Indicates that one entity performs work or exerts effort in order to achieve, support, or contribute to another entity or outcome.
-
E.
worksAgainst
Indicates that one entity actively opposes, counteracts, or undermines the goals, effects, or interests of another entity.
- 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_69f348d892948190915f8facacb9568c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f7516d5b4081908588a6feb541f355 |
completed | May 3, 2026, 1:45 p.m. |
| PD | Predicate disambiguation | batch_69f74d40ebb081909daf60623e38f41d |
completed | May 3, 2026, 1:27 p.m. |
Created at: April 30, 2026, 10:44 p.m.