Triple
T33533258
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tan-y-Deri |
E858852
|
entity |
| Predicate | relativeOfArchitect |
P95351
|
FINISHED |
| Object | Frank Lloyd Wright’s sister |
—
|
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: Frank Lloyd Wright’s sister | Statement: [Tan-y-Deri, relativeOfArchitect, Frank Lloyd Wright’s sister]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeOfArchitect Context triple: [Tan-y-Deri, relativeOfArchitect, Frank Lloyd Wright’s sister]
-
A.
hasRelationToArchitect
chosen
Indicates that one entity has a specified relationship or association with an architect.
-
B.
architecturalRole
Indicates the functional or design-related role that one entity plays within the structure, layout, or organization of another entity.
-
C.
relatedWorkOfArchitect
Indicates that one work is related to, associated with, or otherwise connected in context or authorship to an architect.
-
D.
architecturalCollaborator
Indicates a relationship where one entity works jointly with another on architectural design, planning, or related architectural activities.
-
E.
coArchitectOf
Indicates a relationship where two or more entities jointly serve as architects of the same project, design, 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_69f34978caf4819083f90eba4944d8e8 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379f505c88190ac0879ab422c3054 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:39 a.m.