Triple
T9587761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cathedral of Jaca |
E231333
|
entity |
| Predicate | hasPortalStyle |
P1609
|
FINISHED |
| Object | Romanesque sculpted portal |
—
|
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: Romanesque sculpted portal | Statement: [Cathedral of Jaca, hasPortalStyle, Romanesque sculpted portal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPortalStyle Context triple: [Cathedral of Jaca, hasPortalStyle, Romanesque sculpted portal]
-
A.
hasPortal
Indicates that one entity possesses or provides access to a portal connecting to another location or entity.
-
B.
hasStyle
chosen
Indicates that an entity possesses, exhibits, or is characterized by a particular style or manner.
-
C.
hasPortico
Indicates that one entity (typically a building or structure) features a portico as part of its architectural design.
-
D.
hasMainPortal
Indicates that one entity serves as the primary or main portal (entry point or access interface) for another entity.
-
E.
hasSystemStyle
Indicates that one entity is associated with, or characterized by, a particular system-defined style of another entity.
- 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_69ca848161688190a68d514a0a9d5129 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd99f01ca08190afaa44645a58e918 |
completed | April 1, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69ccd59fd7408190b36831902e3f37f7 |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:06 p.m.