Triple
T215978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sydney Opera House |
E4105
|
entity |
| Predicate | architecturalFeature |
P6684
|
FINISHED |
| Object | shell-like roof |
—
|
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: shell-like roof | Statement: [Sydney Opera House, architecturalFeature, shell-like roof]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: architecturalFeature Context triple: [Sydney Opera House, architecturalFeature, shell-like roof]
-
A.
hasArchitecturalFeature
chosen
Indicates that one entity possesses, includes, or is characterized by a specific architectural feature or element.
-
B.
architecturalConcept
Indicates that one entity represents or embodies an architectural concept in relation to another entity.
-
C.
architecturalStyle
Indicates the architectural design tradition, movement, or style that characterizes the form and appearance of a structure or built work.
-
D.
architectureType
Indicates the specific style or category of architecture that characterizes or defines an entity.
-
E.
architecturalWork
Indicates that one entity is an architectural creation (such as a building or structure) designed or realized by another entity.
- 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_69a2573508588190b522c2476d91acfe |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25dcd2b208190855d5d8d70a3acfc |
completed | Feb. 28, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69a25b52190481908f299d26122bafd2 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.