Triple
T16838393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Messina Cathedral |
E409341
|
entity |
| Predicate | clockTowerLocation |
P2494
|
FINISHED |
| Object | campanile adjacent to the cathedral |
—
|
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: campanile adjacent to the cathedral | Statement: [Messina Cathedral, clockTowerLocation, campanile adjacent to the cathedral]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clockTowerLocation Context triple: [Messina Cathedral, clockTowerLocation, campanile adjacent to the cathedral]
-
A.
hasClockTower
chosen
Indicates that one entity possesses or features a clock tower as part of its structure or property.
-
B.
clockTowerAdded
Indicates that a clock tower has been newly constructed or incorporated into an existing structure or location.
-
C.
towerLocation
Indicates that a tower is located at, or associated with, a specific place or geographic location.
-
D.
hasBellTowerLocation
Indicates the specific location where a bell tower is situated or attached relative to another structure or place.
-
E.
emblematicBuildingLocation
Indicates that a building serves as a symbolic or representative landmark for a particular location or area.
- 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_69d883952b048190887740a980b712ed |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b34ed7d48190a5f8d9f03a332a22 |
completed | April 18, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_69e32b87b4248190aaddb05e88452356 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:23 a.m.