Triple
T451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard University |
E9
|
entity |
| Predicate | campusType |
P110
|
FINISHED |
| Object | urban campus |
—
|
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: urban campus | Statement: [Harvard University, campusType, urban campus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campusType Context triple: [Harvard University, campusType, urban campus]
-
A.
campusSize
Indicates the physical extent or scale of a campus, typically measured in area or capacity.
-
B.
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.
-
C.
academicDegree
Indicates that an entity holds or has been awarded a specific academic degree.
-
D.
offersDegree
Indicates that an institution or program provides a specific academic degree as an available qualification.
-
E.
educatedAt
Indicates that an entity received education or formal training at a specified institution or place of learning.
- 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_69a22735e1b081908bd0457057dcf086 |
completed | Feb. 27, 2026, 11:22 p.m. |
| NER | Named-entity recognition | batch_69a2304aaa2c8190ab7e8dd5da977c11 |
completed | Feb. 28, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69a22918087081909e717b8bee896e8f |
completed | Feb. 27, 2026, 11:30 p.m. |
| PDg | Predicate description generation | batch_69a23049fde881908c53b5d18ebc73d0 |
completed | Feb. 28, 2026, 12:01 a.m. |
Created at: Feb. 27, 2026, 11:24 p.m.