Triple
T4994296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pergamon Altar frieze |
E112205
|
entity |
| Predicate | museumDisplayType |
P61368
|
FINISHED |
| Object | reconstructed architectural setting |
—
|
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: reconstructed architectural setting | Statement: [Pergamon Altar frieze, museumDisplayType, reconstructed architectural setting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: museumDisplayType Context triple: [Pergamon Altar frieze, museumDisplayType, reconstructed architectural setting]
-
A.
hasMuseumType
Indicates that an entity is classified as a museum of a specific type or category.
-
B.
museumSection
Indicates that one entity is a section, area, or subdivision within a museum associated with the other entity.
-
C.
museumHolds
Indicates that a museum possesses, preserves, or has custody of a particular item or collection within its holdings.
-
D.
exhibitionType
Indicates the specific category or kind of exhibition associated with an entity (e.g., art show, trade fair, scientific exhibit).
-
E.
exhibitStyle
Indicates that an entity displays, demonstrates, or embodies a particular style or manner of expression.
- F. None of above. chosen
Provenance (4 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_69bd4432b32c81909f3b3c6bd10f0653 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7472a1dc8190942f568a81fdd961 |
completed | March 20, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69bd714aee2481908fb0dd5fa2daf3a1 |
completed | March 20, 2026, 4:09 p.m. |
| PDg | Predicate description generation | batch_69bd74713fc88190916c2b04cd2e677e |
completed | March 20, 2026, 4:23 p.m. |
Created at: March 20, 2026, 1:34 p.m.