Triple
T8653561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Hephaestus |
E205156
|
entity |
| Predicate | friezeType |
P9591
|
FINISHED |
| Object | Doric frieze with triglyphs and metopes |
—
|
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: Doric frieze with triglyphs and metopes | Statement: [Temple of Hephaestus, friezeType, Doric frieze with triglyphs and metopes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: friezeType Context triple: [Temple of Hephaestus, friezeType, Doric frieze with triglyphs and metopes]
-
A.
hasFrieze
chosen
Indicates that one entity features or is adorned with a frieze associated with another entity.
-
B.
exhibitionType
Indicates the specific category or kind of exhibition associated with an entity (e.g., art show, trade fair, scientific exhibit).
-
C.
furnishingType
Indicates the type or category of furnishings associated with an entity, such as a property or room.
-
D.
exhibitionSpaceType
Indicates the specific kind or category of space used to display or present exhibitions.
-
E.
exhibitionMedium
Indicates the material or format through which something is exhibited or displayed.
- 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_69ca834e56848190abb0eeaec9dedd32 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc484206d881908017897dada63124 |
completed | March 31, 2026, 10:18 p.m. |
| PD | Predicate disambiguation | batch_69cc45619460819091e83ffdec99c865 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:29 p.m.