Triple
T15056087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Girard College |
E379494
|
entity |
| Predicate | campusLayout |
P27120
|
FINISHED |
| Object | quadrangular plan centered on Founders Hall |
—
|
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: quadrangular plan centered on Founders Hall | Statement: [Girard College, campusLayout, quadrangular plan centered on Founders Hall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campusLayout Context triple: [Girard College, campusLayout, quadrangular plan centered on Founders Hall]
-
A.
campusStructure
Indicates a structural or organizational relationship between parts of a campus and the campus as a whole (e.g., buildings, facilities, or areas belonging to or forming the campus).
-
B.
campusLandmark
Indicates that something serves as a notable or recognizable landmark located on or associated with a campus.
-
C.
cityCampus
Indicates that a campus is located within or associated with a particular city.
-
D.
campusArea
Indicates that one entity is the physical area or spatial extent of a campus associated with another entity.
-
E.
campusDesign
chosen
Indicates the relationship between an educational institution and the overall planning, layout, and architectural design of its campus environment.
- 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_69d85cd64d108190853797a95c11cc45 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69deda937f788190899d81bbb2084443 |
completed | April 15, 2026, 12:23 a.m. |
| PD | Predicate disambiguation | batch_69deb95a182081908fffc4402b02a394 |
completed | April 14, 2026, 10:02 p.m. |
Created at: April 10, 2026, 3:01 a.m.