Triple
T36628083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isleworth Mona Lisa |
E904229
|
entity |
| Predicate | hasBeenExhibited |
P25599
|
FINISHED |
| Object | public exhibitions in the 20th century |
—
|
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: public exhibitions in the 20th century | Statement: [Isleworth Mona Lisa, hasBeenExhibited, public exhibitions in the 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBeenExhibited Context triple: [Isleworth Mona Lisa, hasBeenExhibited, public exhibitions in the 20th century]
-
A.
hasExhibitedAt
chosen
Indicates that an entity has displayed or presented its work at a particular event, venue, or exhibition.
-
B.
exhibitedBefore
Indicates that one entity was displayed, presented, or shown to an audience earlier in time than another entity.
-
C.
hasExhibition
Indicates that an entity organizes, hosts, or presents a particular exhibition.
-
D.
exhibitedFor
Indicates that something is displayed, presented, or shown for the benefit, use, or consideration of a particular audience, purpose, or entity.
-
E.
hasExhibitionsAbout
Indicates that one entity organizes or presents exhibitions whose subject matter concerns another entity.
- 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_69f76e6ae750819096911e6e2d4d12c5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
Created at: May 3, 2026, 4:11 p.m.