Triple
T5048507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hydropolis |
E113726
|
entity |
| Predicate | usesExhibitType |
P54449
|
FINISHED |
| Object | interactive installations |
—
|
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: interactive installations | Statement: [Hydropolis, usesExhibitType, interactive installations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesExhibitType Context triple: [Hydropolis, usesExhibitType, interactive installations]
-
A.
canExhibit
Indicates that one entity has the ability or potential to display, manifest, or show a particular property, behavior, or characteristic.
-
B.
hasExhibitCategory
chosen
Indicates that an exhibit is associated with a particular category or type of exhibit.
-
C.
hasExhibits
Indicates that an entity (such as a museum, gallery, or event) displays or presents certain items, artworks, or objects as part of its collection or show.
-
D.
usedByExhibitorType
Indicates that something is utilized or applied by a specific type or category of exhibitor.
-
E.
hasExhibitFormat
Indicates the specific format or medium in which an exhibit is presented or made available.
- 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_69bd44391fc48190a311ce9c826c209b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7401419081909ba62b9c27f770c4 |
completed | March 20, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69bd715479f08190933604aebd34414f |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:37 p.m.