Triple
T6292744
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spanish Colonial architecture |
E141057
|
entity |
| Predicate | hasTypicalRoofType |
P62170
|
FINISHED |
| Object | red-tile 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: red-tile roof | Statement: [Spanish Colonial architecture, hasTypicalRoofType, red-tile roof]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalRoofType Context triple: [Spanish Colonial architecture, hasTypicalRoofType, red-tile roof]
-
A.
roofTypeTypical
chosen
Indicates that a specified roof type is the common or characteristic roof style typically found for a given context or entity.
-
B.
hasIconicRoofShape
Indicates that an entity possesses a roof with a distinctive, widely recognized, or characteristic shape.
-
C.
hasRooftop
Indicates that one entity possesses or is equipped with a rooftop as a structural feature.
-
D.
roofStatus
Indicates the current condition or state of a roof, such as whether it is intact, damaged, under repair, or replaced.
-
E.
roofFeature
Indicates that one entity is a feature, element, or characteristic that is part of or associated with a roof.
- 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_69c008cdf2ac8190bb640c94478fb4ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0642017588190b6c99c685653f6c2 |
completed | March 22, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69c060df0d8881908215575862ef6831 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:27 p.m.