Triple
T26511777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palazzo della Carovana |
E669702
|
entity |
| Predicate | facedOn |
P143462
|
FINISHED |
| Object | Piazza dei Cavalieri |
—
|
NE NERFINISHED |
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: Piazza dei Cavalieri | Statement: [Palazzo della Carovana, facedOn, Piazza dei Cavalieri]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: facedOn Context triple: [Palazzo della Carovana, facedOn, Piazza dei Cavalieri]
-
A.
facedBy
Indicates that one entity is oriented toward and directly opposite another entity, such that it is facing it.
-
B.
isFaceOn
chosen
Indicates that one surface or side of an object is oriented directly toward, or aligned to face, another object or reference direction.
-
C.
defacedWith
Indicates that one entity has been damaged, marred, or vandalized using another entity as the means or material of defacement.
-
D.
facedEvent
Indicates that an entity directly encountered, experienced, or dealt with a particular event.
-
E.
designedToFace
Indicates that one entity has been intentionally oriented or configured so that its front, surface, or primary direction points toward another entity or reference direction.
- F. None of above.
Provenance (3 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_69eeb319ec70819090834c2591cf5f1e |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61392ec5081909382ace560650d77 |
completed | May 2, 2026, 3:09 p.m. |
| PD | Predicate disambiguation | batch_69f60b89cc048190a9feb24466006be0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 1:20 a.m.