Triple
T2828078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kinkaku-ji |
E54970
|
entity |
| Predicate | materialOfUpperFloors |
P11118
|
FINISHED |
| Object | wood covered with gold leaf |
—
|
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 covered with gold leaf | Statement: [Kinkaku-ji, materialOfUpperFloors, wood covered with gold leaf]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: materialOfUpperFloors Context triple: [Kinkaku-ji, materialOfUpperFloors, wood covered with gold leaf]
-
A.
hasFloorMaterial
chosen
Indicates that an entity’s floor is made of, covered with, or constructed from a specified material.
-
B.
ceilingMaterial
Indicates the material from which a ceiling is constructed or finished.
-
C.
streetMaterial
Indicates the material composition from which a street or road surface is made.
-
D.
hasUpperFloor
Indicates that one entity possesses or includes an upper floor relative to another level or reference point.
-
E.
exteriorMaterial
Indicates the material that forms the outer surface or outer construction of an object or structure.
- 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_69ab49e100c0819082a40cb797383243 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abde95d8148190bcae8b0659a5c116 |
completed | March 7, 2026, 8:15 a.m. |
| PD | Predicate disambiguation | batch_69abdd0acab881909e8c25cbef83678c |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 9:59 p.m.