Triple
T6398683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Piazza Colonna |
E144003
|
entity |
| Predicate | adjacentBuildingFunction |
P70406
|
FINISHED |
| Object | Italian Prime Minister’s office |
—
|
LITERAL FINISHED |
How this triple was built (2 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: Italian Prime Minister’s office | Statement: [Piazza Colonna, adjacentBuildingFunction, Italian Prime Minister’s office]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adjacentBuildingFunction Context triple: [Piazza Colonna, adjacentBuildingFunction, Italian Prime Minister’s office]
-
A.
isAdjacentTo
Indicates that one entity is directly next to or bordering another without anything of the same type in between.
-
B.
adjacentFacilitySecurityClass
Indicates that two facilities located next to each other share a specified level or classification of security.
-
C.
adjacentToInfrastructure
Indicates that one entity is located directly next to or in immediate proximity to a piece of infrastructure.
-
D.
adjacentLandmark
Indicates that one landmark is located directly next to or very near another landmark, with no significant separation between them.
-
E.
floorCountOfSurroundingBuildings
Indicates the number of floors in the buildings that are located around or near a given reference building or area.
- F. None of above. chosen
Provenance (4 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_69c008dc56fc81908d43ffcc11d73bdd |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c06897ebc48190842d48cce469eba5 |
completed | March 22, 2026, 10:09 p.m. |
| PD | Predicate disambiguation | batch_69c060f25c088190b433f78553ff1d84 |
completed | March 22, 2026, 9:36 p.m. |
| PDg | Predicate description generation | batch_69c0623d23448190a75cf5d802fc0a02 |
completed | March 22, 2026, 9:42 p.m. |
Created at: March 22, 2026, 4:35 p.m.