Triple
T8386251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | cathedral complex of Trier |
E197824
|
entity |
| Predicate | containsArtworksFrom |
P70602
|
FINISHED |
| Object | Romanesque period |
—
|
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: Romanesque period | Statement: [cathedral complex of Trier, containsArtworksFrom, Romanesque period]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsArtworksFrom Context triple: [cathedral complex of Trier, containsArtworksFrom, Romanesque period]
-
A.
includesArtBy
chosen
Indicates that one entity contains, features, or presents artwork created by another entity.
-
B.
associatedWithWorkOfArt
Indicates a relationship in which an entity is connected or related to a specific work of art, such as through creation, contribution, ownership, or contextual association.
-
C.
appearsInWorkOfArt
Indicates that an entity is depicted, represented, or otherwise featured within a particular work of art.
-
D.
partOfArtistOeuvre
Indicates that something (such as a work or piece) belongs to and is included within an artist’s overall body of work.
-
E.
exhibitsWorkOf
Indicates that one entity displays or presents the creative works produced by 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_69ca82f749388190bffbea6dfb509016 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb80e1bcdc81909111aa33ee996e0a |
completed | March 31, 2026, 8:08 a.m. |
| PD | Predicate disambiguation | batch_69cb70cfe82881909fe374ba52649e84 |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6:02 p.m.