Triple
T17555246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aqueduct of Morelia |
E427573
|
entity |
| Predicate | isPartOfUrbanLandscape |
P119773
|
FINISHED |
| Object | Morelia historic urban fabric |
—
|
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: Morelia historic urban fabric | Statement: [Aqueduct of Morelia, isPartOfUrbanLandscape, Morelia historic urban fabric]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfUrbanLandscape Context triple: [Aqueduct of Morelia, isPartOfUrbanLandscape, Morelia historic urban fabric]
-
A.
isInUrbanContext
Indicates that something exists, occurs, or is situated within an urban or city-based environment or setting.
-
B.
isUrbanStreet
Indicates that a given street is located within an urban area or city environment rather than a rural or suburban setting.
-
C.
isPartOfStreetscape
Indicates that something forms a component or element within the overall layout or visual composition of a streetscape.
-
D.
partOfUrbanLayout
chosen
Indicates that one entity is a component or constituent element within the overall structure or organization of an urban area.
-
E.
isUrbanPark
Indicates that a location is designated and used as a public park within an urban or metropolitan 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_69d889df6dc081908f67dbadc03c07ee |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4562205c08190a7580a762d61b1e3 |
completed | April 19, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fb39948190a82a597c5bac5c57 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:50 a.m.