Triple
T3924399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | France Pavilion (Expo 67) |
E93238
|
entity |
| Predicate | exhibitionCategory |
P3934
|
FINISHED |
| Object | temporary structure |
—
|
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: temporary structure | Statement: [France Pavilion (Expo 67), exhibitionCategory, temporary structure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exhibitionCategory Context triple: [France Pavilion (Expo 67), exhibitionCategory, temporary structure]
-
A.
exhibitionType
chosen
Indicates the specific category or kind of exhibition associated with an entity (e.g., art show, trade fair, scientific exhibit).
-
B.
exhibition
Indicates that an entity is organizing, hosting, or serving as a public display or presentation of another entity (such as artworks, objects, or information).
-
C.
exhibitionMedium
Indicates the material or format through which something is exhibited or displayed.
-
D.
exhibitionGalleries
Indicates that an exhibition is displayed or hosted in one or more specific galleries.
-
E.
exhibitionSource
Indicates the origin or provider from which an exhibition or displayed work is sourced or obtained.
- 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_69aed96bfa1081908f7b30f2c647dee6 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeed7dacdc8190854ebc13db2d24bc |
completed | March 9, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69aee7609c4081908000ce12ae827c3f |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:23 p.m.