Triple
T24527216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaohsiung Exhibition Center |
E606699
|
entity |
| Predicate | hasIndoorSpaceType |
P94573
|
FINISHED |
| Object | exhibition hall |
—
|
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: exhibition hall | Statement: [Kaohsiung Exhibition Center, hasIndoorSpaceType, exhibition hall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIndoorSpaceType Context triple: [Kaohsiung Exhibition Center, hasIndoorSpaceType, exhibition hall]
-
A.
hasIndoorType
chosen
Indicates that an entity is associated with a specific type or category of indoor environment or indoor feature.
-
B.
hasIndoorArea
Indicates that an entity possesses or includes an area or space that is located indoors or within a building.
-
C.
hasOutdoorSpaceType
Indicates the specific kind of outdoor area associated with an entity, such as a balcony, terrace, garden, or patio.
-
D.
indoorOrOutdoor
Indicates whether an activity, event, or entity occurs inside a building (indoors) or outside in open air (outdoors).
-
E.
hasIndoorCounterpart
Indicates that something has a corresponding or equivalent version designed for use indoors.
- 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_69e2c4c85778819085f5da9af3569ad5 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b0ca8081908d931aec560eae56 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:25 a.m.