Triple
T21514585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oltrarno |
E530809
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Porta San Niccolò
Porta San Niccolò is a historic medieval city gate and tower in Florence, Italy, located in the Oltrarno district along the Arno River.
|
E1489447
|
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: Porta San Niccolò | Statement: [Oltrarno, contains, Porta San Niccolò]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Porta San Niccolò Context triple: [Oltrarno, contains, Porta San Niccolò]
-
A.
Porta San Pellegrino
Porta San Pellegrino is a small historic gate in the Vatican City walls that provides access near St. Peter’s Basilica and the surrounding Vatican area.
-
B.
Porta San Donato
Porta San Donato is a historic city gate in Lucca, Italy, serving as one of the main entrances through the town’s Renaissance-era defensive walls.
-
C.
Porta di San Leonardo
Porta di San Leonardo is a historic city gate in Viterbo, Italy, forming part of the town’s medieval defensive walls.
-
D.
Porta San Marco
Porta San Marco is a historic city gate in Viterbo, Italy, forming part of the town’s medieval defensive walls.
-
E.
Porta delle Fonti
Porta delle Fonti is a historic medieval gate in San Gimignano, Italy, leading to the town’s ancient public fountains and water sources.
- 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: Porta San Niccolò Triple: [Oltrarno, contains, Porta San Niccolò]
Generated description
Porta San Niccolò is a historic medieval city gate and tower in Florence, Italy, located in the Oltrarno district along the Arno River.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Porta San Niccolò Target entity description: Porta San Niccolò is a historic medieval city gate and tower in Florence, Italy, located in the Oltrarno district along the Arno River.
-
A.
Porta San Pellegrino
Porta San Pellegrino is a small historic gate in the Vatican City walls that provides access near St. Peter’s Basilica and the surrounding Vatican area.
-
B.
Porta San Donato
Porta San Donato is a historic city gate in Lucca, Italy, serving as one of the main entrances through the town’s Renaissance-era defensive walls.
-
C.
Porta di San Leonardo
Porta di San Leonardo is a historic city gate in Viterbo, Italy, forming part of the town’s medieval defensive walls.
-
D.
Porta San Marco
Porta San Marco is a historic city gate in Viterbo, Italy, forming part of the town’s medieval defensive walls.
-
E.
Porta delle Fonti
Porta delle Fonti is a historic medieval gate in San Gimignano, Italy, leading to the town’s ancient public fountains and water sources.
- 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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea89b6e48190ac4ea139b895714f |
completed | April 23, 2026, 9:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09e820c650819098fa5816e87486bf |
completed | May 17, 2026, 4:09 p.m. |
| NEDg | Description generation | batch_6a09e9da344481909165fe1e17dfb6c3 |
completed | May 17, 2026, 4:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09eaa19be8819084e336cba321505e |
completed | May 17, 2026, 4:19 p.m. |
Created at: April 16, 2026, 6:25 p.m.