Triple
T8780014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Churaumi Aquarium |
E208700
|
entity |
| Predicate | OkichanTheaterFeatures |
P85340
|
FINISHED |
| Object | dolphin shows |
—
|
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: dolphin shows | Statement: [Churaumi Aquarium, OkichanTheaterFeatures, dolphin shows]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: OkichanTheaterFeatures Context triple: [Churaumi Aquarium, OkichanTheaterFeatures, dolphin shows]
-
A.
isPartOfTheater
Indicates that one entity functions as a component, section, or subdivision within a larger theater (such as a theater building, complex, or organizational unit).
-
B.
theaterType
Indicates the specific kind or category of theater associated with an entity (e.g., cinema, opera house, drama theater).
-
C.
theaterWork
Indicates a relationship where an entity is a theatrical work (such as a play or stage production) associated with another entity, typically as its subject, creator, or context.
-
D.
theaterFocus
Indicates a relationship where an entity’s primary attention, activity, or specialization is centered on theater or theatrical performance.
-
E.
theatreType
Indicates the specific category or kind of theatre associated with an entity, such as its format, style, or operational model.
- 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_69ca835fbee88190bf625939bac48d7f |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5f548aa48190b2e73f292758e361 |
completed | March 31, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69cc5c1aff3881908be6a9cbc9f50461 |
completed | March 31, 2026, 11:43 p.m. |
| PDg | Predicate description generation | batch_69cc5cfddef48190aee764ee7b25bae9 |
completed | March 31, 2026, 11:47 p.m. |
Created at: March 30, 2026, 6:42 p.m.