Triple
T2394937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rimini |
E47626
|
entity |
| Predicate | twinCity |
P1072
|
FINISHED |
| Object |
Pula
Pula is a historic coastal city in Croatia known for its well-preserved Roman amphitheater and Adriatic seaside location.
|
E262587
|
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: Pula | Statement: [Rimini, twinCity, Pula]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pula Context triple: [Rimini, twinCity, Pula]
-
A.
Kwaluseni
Kwaluseni is a town in Eswatini known primarily as the main campus site of the University of Eswatini.
-
B.
Ulundi
Ulundi is a historic town in KwaZulu-Natal, South Africa, best known as the former royal and political center of the Zulu Kingdom and the site of key events in the Anglo-Zulu War.
-
C.
Siyani
Siyani is a given name most notably associated with Siyani Chambers, an American basketball player known for his collegiate career at Harvard University.
-
D.
Lilangeni
The lilangeni is the official monetary unit of Eswatini, subdivided into 100 cents and commonly used alongside the South African rand.
-
E.
Masandawana
Masandawana is the popular nickname of South African football club Mamelodi Sundowns F.C., one of the country’s most successful and widely supported teams.
- 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: Pula Triple: [Rimini, twinCity, Pula]
Generated description
Pula is a historic coastal city in Croatia known for its well-preserved Roman amphitheater and Adriatic seaside location.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Pula Target entity description: Pula is a historic coastal city in Croatia known for its well-preserved Roman amphitheater and Adriatic seaside location.
-
A.
Kwaluseni
Kwaluseni is a town in Eswatini known primarily as the main campus site of the University of Eswatini.
-
B.
Ulundi
Ulundi is a historic town in KwaZulu-Natal, South Africa, best known as the former royal and political center of the Zulu Kingdom and the site of key events in the Anglo-Zulu War.
-
C.
Siyani
Siyani is a given name most notably associated with Siyani Chambers, an American basketball player known for his collegiate career at Harvard University.
-
D.
Lilangeni
The lilangeni is the official monetary unit of Eswatini, subdivided into 100 cents and commonly used alongside the South African rand.
-
E.
Masandawana
Masandawana is the popular nickname of South African football club Mamelodi Sundowns F.C., one of the country’s most successful and widely supported teams.
- 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_69a88a1c450c81909f61abb8b6863885 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc879b1b88190be8d0337d9a17bd0 |
completed | March 7, 2026, 6:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aeb3dc44dc819099b8914b878c5638 |
completed | March 9, 2026, 11:49 a.m. |
| NEDg | Description generation | batch_69aeb4de29988190ae860fc6f241f225 |
completed | March 9, 2026, 11:54 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69aeb562560c8190a03c6d8ce6d75956 |
completed | March 9, 2026, 11:56 a.m. |
Created at: March 4, 2026, 7:57 p.m.