Triple
T27116503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Czechoslovak Pavilion |
E686859
|
entity |
| Predicate | expoEdition |
P161867
|
FINISHED |
| Object | Expo 58 Brussels World’s Fair |
—
|
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: Expo 58 Brussels World’s Fair | Statement: [Czechoslovak Pavilion, expoEdition, Expo 58 Brussels World’s Fair]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: expoEdition Context triple: [Czechoslovak Pavilion, expoEdition, Expo 58 Brussels World’s Fair]
-
A.
specialEdition
Indicates that an item is a distinct, limited, or enhanced version of a standard release, often with unique features, packaging, or content.
-
B.
expandedEditionIncludes
Indicates that an expanded edition of a work contains, as part of its content, the material from another specified edition or version.
-
C.
exhibitFor
Indicates a relationship where something is displayed, presented, or shown for the benefit, use, or consideration of a particular audience, purpose, or entity.
-
D.
expandedEditionYear
Indicates the year in which a work’s expanded or enlarged edition was published or released.
-
E.
exhibitionFeature
Indicates that an exhibition includes or highlights a particular item, work, or element as one of its featured components.
- 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_69ef148c2b588190afc15b529f7af845 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f624069afc8190916ff8dc2e4a3a1a |
completed | May 2, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69f61b40f02081909bd9c3ea73249163 |
completed | May 2, 2026, 3:41 p.m. |
| PDg | Predicate description generation | batch_69f61fa35ac48190890102c348ed81a0 |
completed | May 2, 2026, 4 p.m. |
Created at: April 27, 2026, 8:56 a.m.