Triple
T21706525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ionian order |
E535783
|
entity |
| Predicate | hasEntablatureFeature |
P80972
|
FINISHED |
| Object | three‑fascia architrave |
—
|
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: three‑fascia architrave | Statement: [Ionian order, hasEntablatureFeature, three‑fascia architrave]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEntablatureFeature Context triple: [Ionian order, hasEntablatureFeature, three‑fascia architrave]
-
A.
entablatureType
chosen
Indicates the specific architectural style or form of an entablature used in relation to a structure or element.
-
B.
entablatureSimilarTo
Indicates that one entablature shares similar design, structure, or stylistic features with another entablature.
-
C.
hasFrets
Indicates that an instrument or similar object possesses frets, i.e., raised elements on its neck or surface that divide it into fixed pitch intervals.
-
D.
hasFingeringSystem
Indicates that an instrument or object is associated with a particular method or system for positioning fingers to produce notes or actions.
-
E.
hasTuningDivision
Indicates that one entity specifies or uses a particular system or scheme for dividing a range (such as a musical interval or scale) into tuning units.
- 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_69e0c46b44c0819088ab883ebd44e0e8 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69efb52f64c48190b5d59561999e922f |
completed | April 27, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69e6969113cc8190ab69855ef5667e4b |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:46 p.m.