Triple
T35221672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rokuon-ji |
E1016973
|
entity |
| Predicate | principalBuilding |
P39867
|
FINISHED |
| Object | Kinkaku-ji |
—
|
NE NERFINISHED |
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: Kinkaku-ji | Statement: [Rokuon-ji, principalBuilding, Kinkaku-ji]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: principalBuilding Context triple: [Rokuon-ji, principalBuilding, Kinkaku-ji]
-
A.
publicBuilding
Indicates that a building is designated for public use or access, typically serving communal, governmental, or civic functions.
-
B.
isMainBuildingOf
chosen
Indicates that a building serves as the primary or central facility associated with a particular organization, complex, or site.
-
C.
capitalBuilding
Indicates that a building serves as the primary governmental or administrative center (capital building) for a political region or entity.
-
D.
mainBuildingName
Indicates the name that is designated as the primary or main building associated with an entity.
-
E.
originalBuilding
Indicates that a building is the initial or first version from which later buildings, modifications, or replacements are derived.
- 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_69f76de072908190ab65038a8a7b6a79 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f79533b88c8190934ec4cb21770e24 |
completed | May 3, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69f79104f5b48190a496cdffde8472da |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:02 p.m.