Triple
T4238472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aqua Paola aqueduct |
E94750
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object |
Acqua di Paolo
Acqua di Paolo is a historic Baroque-era aqueduct in Rome, Italy, renowned for supplying water to the city and feeding the monumental Fontana dell’Acqua Paola on the Janiculum Hill.
|
E423496
|
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: Acqua di Paolo | Statement: [Aqua Paola aqueduct, alsoKnownAs, Acqua di Paolo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Acqua di Paolo Context triple: [Aqua Paola aqueduct, alsoKnownAs, Acqua di Paolo]
-
A.
Venini
Venini is a renowned Italian glassmaking company based in Murano, celebrated for its innovative and artistic blown-glass designs.
-
B.
Looz
Looz is the historical name of the medieval County of Loon, a former principality in what is now eastern Belgium.
-
C.
Aqua Anio Vetus
Aqua Anio Vetus was one of ancient Rome’s earliest major aqueducts, channeling water from the Aniene River to supply the growing city.
-
D.
Bollea
Bollea is the Italian-origin surname of professional wrestling icon Hulk Hogan, whose real name is Terry Bollea.
-
E.
Musso
Musso is a small town on the western shore of Lake Como in northern Italy, known for its scenic lakeside setting and historic connections.
- 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: Acqua di Paolo Triple: [Aqua Paola aqueduct, alsoKnownAs, Acqua di Paolo]
Generated description
Acqua di Paolo is a historic Baroque-era aqueduct in Rome, Italy, renowned for supplying water to the city and feeding the monumental Fontana dell’Acqua Paola on the Janiculum Hill.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Acqua di Paolo Target entity description: Acqua di Paolo is a historic Baroque-era aqueduct in Rome, Italy, renowned for supplying water to the city and feeding the monumental Fontana dell’Acqua Paola on the Janiculum Hill.
-
A.
Venini
Venini is a renowned Italian glassmaking company based in Murano, celebrated for its innovative and artistic blown-glass designs.
-
B.
Looz
Looz is the historical name of the medieval County of Loon, a former principality in what is now eastern Belgium.
-
C.
Aqua Anio Vetus
Aqua Anio Vetus was one of ancient Rome’s earliest major aqueducts, channeling water from the Aniene River to supply the growing city.
-
D.
Bollea
Bollea is the Italian-origin surname of professional wrestling icon Hulk Hogan, whose real name is Terry Bollea.
-
E.
Musso
Musso is a small town on the western shore of Lake Como in northern Italy, known for its scenic lakeside setting and historic connections.
- 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_69b34537cc6481909cd0a96acbb33ef7 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e76b6e0819084d0ce137b5ba74e |
completed | March 12, 2026, 11:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5a86c95008190b11832c741a11042 |
completed | March 14, 2026, 6:26 p.m. |
| NEDg | Description generation | batch_69b5a983cfd88190b702c420d6dbc201 |
completed | March 14, 2026, 6:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5aa00bcd88190ad2fba212861c712 |
completed | March 14, 2026, 6:33 p.m. |
Created at: March 12, 2026, 11:05 p.m.