Triple
T29252769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rotunda of Saint George |
E741610
|
entity |
| Predicate | onlySurvivingMinaretIn |
P166779
|
FINISHED |
| Object | Thessaloniki |
—
|
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: Thessaloniki | Statement: [Rotunda of Saint George, onlySurvivingMinaretIn, Thessaloniki]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onlySurvivingMinaretIn Context triple: [Rotunda of Saint George, onlySurvivingMinaretIn, Thessaloniki]
-
A.
isOnlyRemainingActiveMosqueIn
Indicates that a mosque is the sole mosque still functioning and in use within a given place or region.
-
B.
hasMinarets
Indicates that an entity (typically a building) possesses one or more minarets as architectural features.
-
C.
hasMinaretHeightApprox
Indicates that an entity has a minaret whose height is approximately a specified value, allowing for some margin of imprecision.
-
D.
hasNumberOfMinarets
Indicates the specific count of minarets associated with a given entity.
-
E.
minaretBuiltBy
Indicates that a minaret was constructed by a particular agent, such as a person, group, or organization.
- 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_69f0911eba2c8190b07cd2fdf91422c9 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f664aaeec88190afa894d26edbcf8b |
completed | May 2, 2026, 8:55 p.m. |
| PD | Predicate disambiguation | batch_69f660f2e3708190ab658652bcfc04d0 |
completed | May 2, 2026, 8:39 p.m. |
| PDg | Predicate description generation | batch_69f661e9cb308190a56e25dc17df248e |
completed | May 2, 2026, 8:43 p.m. |
Created at: April 28, 2026, 12:35 p.m.