Triple
T25285952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lapidarium with Trajan’s Column replica |
E633939
|
entity |
| Predicate | artifactTypeDisplayed |
P73006
|
FINISHED |
| Object | reliefs |
—
|
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: reliefs | Statement: [Lapidarium with Trajan’s Column replica, artifactTypeDisplayed, reliefs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: artifactTypeDisplayed Context triple: [Lapidarium with Trajan’s Column replica, artifactTypeDisplayed, reliefs]
-
A.
artifactType
chosen
Indicates the specific kind or category of artifact that an entity is classified as.
-
B.
artifactTypeFound
Indicates that a specific type of artifact has been discovered or identified in association with a given context or location.
-
C.
artCategory
Indicates the classification relationship where an artwork is assigned to a particular artistic category or genre.
-
D.
artworkType
Indicates the specific category or kind of artwork that characterizes the relationship between the subject and the artwork.
-
E.
exhibitionType
Indicates the specific category or kind of exhibition associated with an entity (e.g., art show, trade fair, scientific exhibit).
- 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_69e75a9402fc81909362ca85277c06d9 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48e0921ac8190a4a8fec7be7ad8f6 |
completed | May 1, 2026, 11:27 a.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 1:19 p.m.