Triple
T13752140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Cagliari |
E330379
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object |
UniCa
UniCa is the commonly used abbreviation for the University of Cagliari, a public research university located in Cagliari, Italy.
|
E1058978
|
NE FINISHED |
How this triple was built (4 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: UniCa | Statement: [University of Cagliari, shortName, UniCa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UniCa Context triple: [University of Cagliari, shortName, UniCa]
-
A.
UNICA
UNICA is a network of universities from the capitals of Europe that promotes academic collaboration, mobility, and shared higher education policies among its member institutions.
-
B.
UniPG
UniPG is the commonly used abbreviation for the University of Perugia, a historic Italian public university located in Perugia, Umbria.
-
C.
UCA
UCA is a Jesuit-run Central American University in Managua, Nicaragua, known for its strong emphasis on social justice, human rights, and critical scholarship.
-
D.
UCA
UCA is a Spanish public university based in Cádiz, known for its programs in marine sciences, engineering, and humanities.
-
E.
UCA
UCA is the Unicode Collation Algorithm, a Unicode standard that defines a language-independent method for ordering and comparing Unicode text.
- 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: UniCa Triple: [University of Cagliari, shortName, UniCa]
Generated description
UniCa is the commonly used abbreviation for the University of Cagliari, a public research university located in Cagliari, Italy.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: UniCa Target entity description: UniCa is the commonly used abbreviation for the University of Cagliari, a public research university located in Cagliari, Italy.
-
A.
UNICA
UNICA is a network of universities from the capitals of Europe that promotes academic collaboration, mobility, and shared higher education policies among its member institutions.
-
B.
UniPG
UniPG is the commonly used abbreviation for the University of Perugia, a historic Italian public university located in Perugia, Umbria.
-
C.
UCA
UCA is a Jesuit-run Central American University in Managua, Nicaragua, known for its strong emphasis on social justice, human rights, and critical scholarship.
-
D.
UCA
UCA is a Spanish public university based in Cádiz, known for its programs in marine sciences, engineering, and humanities.
-
E.
UCA
UCA is a French public university located in Clermont-Ferrand, known for its research and education across disciplines such as science, health, law, and humanities.
- F. None of above. chosen
Provenance (5 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_69d81c573f288190aa2403d484fa3d49 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0215cfa08190aaed8b089aff217b |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7a8560614819085958205637f3863 |
completed | May 3, 2026, 7:56 p.m. |
| NEDg | Description generation | batch_69f7a8f6833881908bcca35d7d01596a |
completed | May 3, 2026, 7:58 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f7a9c3c6548190802e1163c9c35b67 |
completed | May 3, 2026, 8:02 p.m. |
Created at: April 9, 2026, 10:09 p.m.