Triple
T28130036
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Superflat touring exhibition (2000–2001, Japan and USA) |
E711039
|
entity |
| Predicate | movementPresented |
P165428
|
FINISHED |
| Object | Superflat |
—
|
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: Superflat | Statement: [Superflat touring exhibition (2000–2001, Japan and USA), movementPresented, Superflat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: movementPresented Context triple: [Superflat touring exhibition (2000–2001, Japan and USA), movementPresented, Superflat]
-
A.
movementIn
Indicates a relationship where an entity moves within, into, or inside a specified area, space, or container.
-
B.
movementFor
Indicates that one entity moves on behalf of, in support of, or as a representative action for another entity.
-
C.
movementRepresentedBy
Indicates that a movement or motion of an entity is depicted, encoded, or symbolized by another entity (such as a sign, pattern, or representation).
-
D.
movementDepicted
Indicates that some form of motion or change in position is visually represented or illustrated.
-
E.
movementStatus
Indicates the current state or condition of an entity’s movement, such as whether and how it is moving or stationary.
- 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_69ef9b73bd288190a21ae3d6aa14f386 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f659355a208190be2609ffc7a9c427 |
completed | May 2, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f65875030881909007c502b7dcc998 |
completed | May 2, 2026, 8:03 p.m. |
Created at: April 27, 2026, 9:22 p.m.