Triple
T3846947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hall of Prayer for Good Harvests |
E85192
|
entity |
| Predicate | roofStructure |
P3576
|
FINISHED |
| Object | triple-eaved 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: triple-eaved roof | Statement: [Hall of Prayer for Good Harvests, roofStructure, triple-eaved roof]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roofStructure Context triple: [Hall of Prayer for Good Harvests, roofStructure, triple-eaved roof]
-
A.
roofFeature
chosen
Indicates that one entity is a feature, element, or characteristic that is part of or associated with a roof.
-
B.
buildingStructure
Indicates that one entity is a structural component or physical part that forms, supports, or constitutes the construction of another entity.
-
C.
roofLevel
Indicates the vertical level or story of a building at which the roof is located or begins.
-
D.
roofHeight
Indicates the vertical distance or elevation of a roof relative to a reference level or structure.
-
E.
roofStatus
Indicates the current condition or state of a roof, such as whether it is intact, damaged, under repair, or replaced.
- 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_69aed936de1c81908f91bed80f70abb2 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeebcb069881909d3536b18b7802a7 |
completed | March 9, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69aee750377c8190af70c79768c0edd8 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:18 p.m.