Triple
T28537087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Knesset building, Jerusalem |
E722190
|
entity |
| Predicate | designerOfArtwork |
P21901
|
FINISHED |
| Object | Marc Chagall |
—
|
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: Marc Chagall | Statement: [Knesset building, Jerusalem, designerOfArtwork, Marc Chagall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designerOfArtwork Context triple: [Knesset building, Jerusalem, designerOfArtwork, Marc Chagall]
-
A.
designedBy
Indicates that one entity is the creator, planner, or architect responsible for the form or structure of another entity.
-
B.
creativeArtist
Indicates that one entity is an artist who creates or originates the work, performance, or creative output associated with another entity.
-
C.
artworkBy
chosen
Indicates that one entity is the creator or artist responsible for producing the other entity as an artwork.
-
D.
composerOfDepictingWork
Indicates that an entity is the composer of a musical work that is itself a depiction or representation of another entity or subject.
-
E.
designerNationality
Indicates that a designer has a specific national or country affiliation.
- 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_69f01a5d7ec88190ada2d5be7c06c35d |
completed | April 28, 2026, 2:24 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 28, 2026, 3:32 a.m.