Triple
T2040350
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mosaic |
E44728
|
entity |
| Predicate | developerUnit |
P23778
|
FINISHED |
| Object | National Center for Supercomputing Applications at the University of Illinois at Urbana–Champaign |
E17323
|
NE FINISHED |
How this triple was built (3 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: National Center for Supercomputing Applications at the University of Illinois at Urbana–Champaign | Statement: [Mosaic, developerUnit, National Center for Supercomputing Applications at the University of Illinois at Urbana–Champaign]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: National Center for Supercomputing Applications at the University of Illinois at Urbana–Champaign Context triple: [Mosaic, developerUnit, National Center for Supercomputing Applications at the University of Illinois at Urbana–Champaign]
-
A.
National Center for Supercomputing Applications
chosen
The National Center for Supercomputing Applications is a leading U.S. research institution known for pioneering high-performance computing technologies and software, including early web browser development.
-
B.
National Energy Research Scientific Computing Center
The National Energy Research Scientific Computing Center is a leading U.S. Department of Energy high-performance computing facility that provides advanced computational resources and support for large-scale scientific research.
-
C.
Oak Ridge Leadership Computing Facility
The Oak Ridge Leadership Computing Facility is a U.S. Department of Energy supercomputing center at Oak Ridge National Laboratory that provides some of the world’s most powerful high-performance computing resources for scientific research.
-
D.
Texas Advanced Computing Center
The Texas Advanced Computing Center is a leading high-performance computing and data research facility that provides powerful supercomputing resources and expertise to support advanced scientific and engineering research.
-
E.
Voorhees Computing Center
Voorhees Computing Center is a major academic computing and technology hub on the Rensselaer Polytechnic Institute campus, housing computer labs, networking infrastructure, and related IT services for students and faculty.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: developerUnit Context triple: [Mosaic, developerUnit, National Center for Supercomputing Applications at the University of Illinois at Urbana–Champaign]
-
A.
developmentRole
Indicates that an entity participates in the creation, design, or production of another entity in a specific developmental capacity or function.
-
B.
formerDeveloper
Indicates that an entity previously worked as a developer for another entity but no longer holds that role.
-
C.
laterDeveloper
Indicates that one developer’s work, role, or involvement occurs after another developer in time.
-
D.
coDeveloperOf
Indicates that two or more entities jointly developed or collaborated in creating the same project, product, or work.
-
E.
developmentTeamFor
chosen
Indicates the team responsible for developing or building a particular product, project, or system.
- F. None of above.
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_69a889159ec481908f9e4472d9f480c7 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abbc2c3f6c8190aff07097b2654e52 |
completed | March 7, 2026, 5:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae271399a08190946b315f439b9b2f |
completed | March 9, 2026, 1:49 a.m. |
| PD | Predicate disambiguation | batch_69abb7aa00d4819086d347d9a08f81a0 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:39 p.m.