Triple
T37897762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sogetsu school |
E945327
|
entity |
| Predicate | architect of headquarters building |
P138
|
FINISHED |
| Object | Kenzo Tange |
—
|
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: Kenzo Tange | Statement: [Sogetsu school, architect of headquarters building, Kenzo Tange]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: architect of headquarters building Context triple: [Sogetsu school, architect of headquarters building, Kenzo Tange]
-
A.
architecturalHeadquarters
Indicates the location that serves as the main or primary base of operations for an architectural entity or organization.
-
B.
architectOfMainBuilding
chosen
Indicates that one entity is the architect who designed the main building associated with another entity.
-
C.
architecturalFirmHeadquarters
Indicates the location where an architectural firm’s main offices or central headquarters are based.
-
D.
architectOfFormerBuilding
Indicates that an entity served as the architect of a building that no longer exists or has been replaced.
-
E.
architectOfNewBuilding
Indicates that one entity is the architect responsible for designing a particular new building.
- 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_69f76ef0e8708190987c7254ed8c7abe |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fd2cf39b0c8190811b8a6fa9410560 |
completed | May 8, 2026, 12:23 a.m. |
| PD | Predicate disambiguation | batch_69fd2ad8dd988190a9899701ba00d917 |
completed | May 8, 2026, 12:14 a.m. |
Created at: May 3, 2026, 4:19 p.m.