Triple
T32470315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GSBS Architects |
E829829
|
entity |
| Predicate | buildingTypeDesigned |
P1844
|
FINISHED |
| Object | museums |
—
|
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: museums | Statement: [GSBS Architects, buildingTypeDesigned, museums]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buildingTypeDesigned Context triple: [GSBS Architects, buildingTypeDesigned, museums]
-
A.
houseTypeDesigned
Indicates that an entity (such as an architect or designer) created or specified the design for a particular type of house.
-
B.
buildingType
chosen
Indicates the specific category or function that characterizes what kind of building something is.
-
C.
currentBuildingDesignedBy
Indicates that the building currently associated with an entity was designed by a specified architect or designer.
-
D.
architecturalWorkType
Indicates the specific kind or category of architectural work that characterizes the relationship between entities.
-
E.
buildingRedesignedBy
Indicates that a building has undergone a redesign carried out by the specified agent or designer.
- 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_69f3491ee87c81908cbf5890079c2af6 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c354b42c8190a72d2c0c69babf5e |
completed | May 3, 2026, 3:39 a.m. |
| PD | Predicate disambiguation | batch_69f6bd25bed08190befcabd3a41ffadf |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 12:57 a.m.