Triple
T1084032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trevi Fountain |
E24010
|
entity |
| Predicate | faces |
P1699
|
FINISHED |
| Object |
Palazzo Poli
Palazzo Poli is a historic Roman palace best known as the grand architectural backdrop to the Trevi Fountain.
|
E125243
|
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: Palazzo Poli | Statement: [Trevi Fountain, faces, Palazzo Poli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Palazzo Poli Context triple: [Trevi Fountain, faces, Palazzo Poli]
-
A.
Palazzo Chiericati
Palazzo Chiericati is a Renaissance palace in Vicenza, Italy, celebrated as one of Andrea Palladio’s most important architectural masterpieces.
-
B.
Palazzo Koch
Palazzo Koch is a grand 19th-century neoclassical palace in Rome that serves as the historic headquarters of Italy’s central bank.
-
C.
Palazzo Madama
Palazzo Madama is a historic Renaissance palace in Rome that serves as the seat of the Italian Senate.
-
D.
Palazzo Madama
Palazzo Madama is a historic palace in Turin, Italy, renowned for its layered architectural styles from Roman times to the Baroque era and for housing the city’s Museum of Ancient Art.
-
E.
Palazzo Chigi
Palazzo Chigi is a historic palace in central Rome that serves as the official residence and workplace of the Prime Minister of Italy.
- 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: Palazzo Poli Triple: [Trevi Fountain, faces, Palazzo Poli]
Generated description
Palazzo Poli is a historic Roman palace best known as the grand architectural backdrop to the Trevi Fountain.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Palazzo Poli Target entity description: Palazzo Poli is a historic Roman palace best known as the grand architectural backdrop to the Trevi Fountain.
-
A.
Palazzo Chiericati
Palazzo Chiericati is a Renaissance palace in Vicenza, Italy, celebrated as one of Andrea Palladio’s most important architectural masterpieces.
-
B.
Palazzo Koch
Palazzo Koch is a grand 19th-century neoclassical palace in Rome that serves as the historic headquarters of Italy’s central bank.
-
C.
Palazzo Madama
Palazzo Madama is a historic Renaissance palace in Rome that serves as the seat of the Italian Senate.
-
D.
Palazzo Madama
Palazzo Madama is a historic palace in Turin, Italy, renowned for its layered architectural styles from Roman times to the Baroque era and for housing the city’s Museum of Ancient Art.
-
E.
Palazzo Chigi
Palazzo Chigi is a historic palace in central Rome that serves as the official residence and workplace of the Prime Minister of Italy.
- 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b9608bac819085196cc0f8fbb2e7 |
completed | March 1, 2026, 10:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac42affbac8190b6b16a1d726d0d35 |
completed | March 7, 2026, 3:22 p.m. |
| NEDg | Description generation | batch_69ac44a7a69c8190af5289f6e46d571a |
completed | March 7, 2026, 3:30 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac451af1508190a55c037328b41931 |
completed | March 7, 2026, 3:32 p.m. |
Created at: March 1, 2026, 7:42 p.m.