Triple
T2860
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Pennsylvania |
E53
|
entity |
| Predicate | hasHospital |
P105
|
FINISHED |
| Object |
Hospital of the University of Pennsylvania
The Hospital of the University of Pennsylvania is a major academic medical center in Philadelphia that serves as the primary teaching hospital for the University of Pennsylvania's Perelman School of Medicine.
|
E83
|
NE FINISHED |
How this triple was built (5 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: Hospital of the University of Pennsylvania | Statement: [University of Pennsylvania, hasHospital, Hospital of the University of Pennsylvania]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hospital of the University of Pennsylvania Context triple: [University of Pennsylvania, hasHospital, Hospital of the University of Pennsylvania]
-
A.
University of Pennsylvania
The University of Pennsylvania is a prestigious Ivy League research university in Philadelphia known for its strong programs across disciplines, including engineering, business, law, and medicine.
-
B.
Carnegie Institution of Washington
The Carnegie Institution of Washington is a private, nonprofit scientific research organization founded by Andrew Carnegie that supports advanced research across fields such as astronomy, biology, and earth sciences.
-
C.
Tufts College
Tufts College is a private research university in Medford and Somerville, Massachusetts, known for its strong programs in the liberal arts, sciences, and international relations.
-
D.
Harvard University
Harvard University is a prestigious private Ivy League research university in Cambridge, Massachusetts, renowned for its academic excellence, influential alumni, and historic leadership in higher education.
-
E.
Massachusetts Institute of Technology
The Massachusetts Institute of Technology is a world-renowned research university in Cambridge, Massachusetts, known for its pioneering work in science, engineering, and technology.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Hospital of the University of Pennsylvania Triple: [University of Pennsylvania, hasHospital, Hospital of the University of Pennsylvania]
Generated description
The Hospital of the University of Pennsylvania is a major academic medical center in Philadelphia that serves as the primary teaching hospital for the University of Pennsylvania's Perelman School of Medicine.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hospital of the University of Pennsylvania Target entity description: The Hospital of the University of Pennsylvania is a major academic medical center in Philadelphia that serves as the primary teaching hospital for the University of Pennsylvania's Perelman School of Medicine.
-
A.
University of Pennsylvania
The University of Pennsylvania is a prestigious Ivy League research university in Philadelphia known for its strong programs across disciplines, including engineering, business, law, and medicine.
-
B.
Carnegie Institution of Washington
The Carnegie Institution of Washington is a private, nonprofit scientific research organization founded by Andrew Carnegie that supports advanced research across fields such as astronomy, biology, and earth sciences.
-
C.
Tufts College
Tufts College is a private research university in Medford and Somerville, Massachusetts, known for its strong programs in the liberal arts, sciences, and international relations.
-
D.
Harvard University
Harvard University is a prestigious private Ivy League research university in Cambridge, Massachusetts, renowned for its academic excellence, influential alumni, and historic leadership in higher education.
-
E.
Massachusetts Institute of Technology
The Massachusetts Institute of Technology is a world-renowned research university in Cambridge, Massachusetts, known for its pioneering work in science, engineering, and technology.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHospital Context triple: [University of Pennsylvania, hasHospital, Hospital of the University of Pennsylvania]
-
A.
hasNotableFacility
chosen
Indicates that an entity possesses or hosts a facility that is of particular significance, prominence, or interest.
-
B.
hasSchool
Indicates that an entity possesses, is associated with, or is served by a particular school.
-
C.
administeredBy
Indicates that an action, service, or process is carried out, managed, or overseen by a specified agent or authority.
-
D.
hasMainCampus
Indicates that an educational institution is primarily based at or chiefly associated with a particular campus location.
-
E.
hasRepresentationIn
Indicates that one entity is represented, depicted, or encoded within another entity, such as a concept, object, or data structure having a corresponding representation in a specific medium or context.
- F. None of above.
Provenance (6 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_69a22e0d37588190897cf37a323013f5 |
completed | Feb. 27, 2026, 11:51 p.m. |
| NER | Named-entity recognition | batch_69a2316d88a08190b2e03041674b5674 |
completed | Feb. 28, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a23296d6a881908dbf9acacf9fb94f |
completed | Feb. 28, 2026, 12:11 a.m. |
| NEDg | Description generation | batch_69a23385a92c81909dc72e5193d32d36 |
completed | Feb. 28, 2026, 12:15 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a234b8f2648190881fdeb4a864617f |
completed | Feb. 28, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69a230c3ee4481908216244c38aa8aef |
completed | Feb. 28, 2026, 12:03 a.m. |
Created at: Feb. 27, 2026, 11:55 p.m.