Triple
T27197974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghai Disney Resort |
E683654
|
entity |
| Predicate | hasStageShowVenue |
P112843
|
FINISHED |
| Object | Walt Disney Grand Theatre |
—
|
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: Walt Disney Grand Theatre | Statement: [Shanghai Disney Resort, hasStageShowVenue, Walt Disney Grand Theatre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStageShowVenue Context triple: [Shanghai Disney Resort, hasStageShowVenue, Walt Disney Grand Theatre]
-
A.
hasVenueFor
chosen
Indicates that one entity provides or serves as the location or setting where an event, activity, or function takes place for another entity.
-
B.
hasVenueIn
Indicates that an event, activity, or occurrence takes place at a specific venue located within a particular geographic area or location.
-
C.
hasVenueName
Indicates that an entity has a specific name used to identify the venue where an event or activity takes place.
-
D.
hasVenueOwner
Indicates that a particular venue is owned or controlled by a specific owner.
-
E.
hasQualifyingVenue
Indicates that an entity is associated with a venue that meets specified qualifying criteria or standards.
- 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_69eefad1fd5c8190a4a46ea6afe58bfa |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69fb2e940d5c8190bceae77daf4ef512 |
completed | May 6, 2026, 12:05 p.m. |
| PD | Predicate disambiguation | batch_69f9fec70bd881909c658a3c5020318b |
completed | May 5, 2026, 2:29 p.m. |
Created at: April 27, 2026, 9:35 a.m.