Triple
T4793292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greene Building |
E106652
|
entity |
| Predicate | housesAcademicDiscipline |
P58460
|
FINISHED |
| Object | architecture |
—
|
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: architecture | Statement: [Greene Building, housesAcademicDiscipline, architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: housesAcademicDiscipline Context triple: [Greene Building, housesAcademicDiscipline, architecture]
-
A.
regionOfAcademicFocus
Indicates the academic subject area or discipline that an entity (such as a person or program) primarily concentrates on or specializes in.
-
B.
academicFocus
Indicates the primary field of study, discipline, or subject area that an entity concentrates on academically.
-
C.
academicType
Indicates the specific academic category or classification associated with an entity (such as a work, program, or role).
-
D.
dimensionOfStudy
Indicates the specific field, aspect, or perspective that characterizes or structures a particular study or research activity.
-
E.
academicStructure
Indicates a hierarchical or organizational relationship within an academic system, such as how programs, departments, courses, or degrees are structured and related to one another.
- F. None of above. chosen
Provenance (4 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_69bd43f591c881909e5a532388b0f3f3 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd66072ebc8190ae0e6cef1e7b07e4 |
completed | March 20, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69bd622e1b408190806c15c61519fc74 |
completed | March 20, 2026, 3:05 p.m. |
| PDg | Predicate description generation | batch_69bd631328fc81909b28ae0a2a3ed9bb |
completed | March 20, 2026, 3:09 p.m. |
Created at: March 20, 2026, 1:22 p.m.