Triple
T38285441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinese Pavilion |
E1022193
|
entity |
| Predicate | originalBuildingMaterial |
P152175
|
FINISHED |
| Object | wood |
—
|
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: wood | Statement: [Chinese Pavilion, originalBuildingMaterial, wood]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalBuildingMaterial Context triple: [Chinese Pavilion, originalBuildingMaterial, wood]
-
A.
originalMaterialFor
Indicates that one entity serves as the source or basis material from which another entity is derived, adapted, or created.
-
B.
originalCoreMaterial
chosen
Indicates that something is made from or based on the initial, primary material used before any changes, replacements, or modifications.
-
C.
originalBuilding
Indicates that a building is the initial or first version from which later buildings, modifications, or replacements are derived.
-
D.
roofMaterialOriginal
Indicates the material that was originally used to construct the roof of a structure.
-
E.
originalBuildingType
Indicates the type or category of building that something was initially constructed or designated to be, before any later changes or repurposing.
- 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_69f76df0cddc81908d16c1556ff4097f |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1c850c819088795a7ae59bdeb8 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:30 p.m.