Triple
T33368659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tower of Terror (Tokyo DisneySea) |
E854424
|
entity |
| Predicate | mainArtifact |
P58235
|
FINISHED |
| Object | Shiriki Utundu idol |
—
|
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: Shiriki Utundu idol | Statement: [Tower of Terror (Tokyo DisneySea), mainArtifact, Shiriki Utundu idol]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainArtifact Context triple: [Tower of Terror (Tokyo DisneySea), mainArtifact, Shiriki Utundu idol]
-
A.
majorArtifact
Indicates that one entity is a primary or highly significant artifact associated with, produced by, or central to the other entity.
-
B.
centralArtifact
chosen
Indicates that an artifact serves as the primary or focal object within a given context, structure, or collection.
-
C.
testArtifact
Indicates that an entity serves as an artifact or item used for testing, validation, or experimentation in a process or system.
-
D.
featuresArtifact
Indicates that one entity prominently includes, presents, or showcases another entity as an artifact.
-
E.
mainAssetManaged
Indicates that one entity is responsible for managing another entity that serves as the primary or main asset.
- 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_69f3496bda8c8190bfc8fade9d1b791c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f70fb4f18c819099ef6d9177b7d205 |
completed | May 3, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69f70f3a54d481909ba6bdda3647b761 |
completed | May 3, 2026, 9:02 a.m. |
Created at: May 1, 2026, 1:35 a.m.