Triple
T12932520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Altar of Zeus at Pergamon |
E309418
|
entity |
| Predicate | featuresFrieze |
P9591
|
FINISHED |
| Object | Gigantomachy frieze |
—
|
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: Gigantomachy frieze | Statement: [Altar of Zeus at Pergamon, featuresFrieze, Gigantomachy frieze]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresFrieze Context triple: [Altar of Zeus at Pergamon, featuresFrieze, Gigantomachy frieze]
-
A.
hasFrieze
chosen
Indicates that one entity features or is adorned with a frieze associated with another entity.
-
B.
featuresIn
Indicates that an entity appears or plays a role within another entity, such as a person or element being included in a work, event, or context.
-
C.
featuresItem
Indicates that one entity includes, presents, or highlights another entity as a notable item or component.
-
D.
featuresDecor
Indicates that one entity includes or showcases the decor elements provided or defined by another entity.
-
E.
exhibitionFeature
Indicates that an exhibition includes or highlights a particular item, work, or element as one of its featured components.
- 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_69d7bdfa933c8190b5a27aa4a08a19b7 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97db69f548190a1a693bc0d6c191a |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 5:42 p.m.