Triple
T21948666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint-Sauveur Cathedral |
E542002
|
entity |
| Predicate | baptisteryHasFeature |
P55197
|
FINISHED |
| Object | ancient columns |
—
|
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: ancient columns | Statement: [Saint-Sauveur Cathedral, baptisteryHasFeature, ancient columns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: baptisteryHasFeature Context triple: [Saint-Sauveur Cathedral, baptisteryHasFeature, ancient columns]
-
A.
hasBaptistery
chosen
Indicates that an entity includes, contains, or is associated with a baptistery as part of its structure or facilities.
-
B.
cathedralFeature
Indicates that one entity is a distinctive architectural or structural feature of a cathedral.
-
C.
hasSacristy
Indicates that a religious building includes or is associated with a sacristy (a room where sacred vessels, vestments, and liturgical items are kept and prepared).
-
D.
hasBasilica
Indicates that one entity possesses, contains, or is associated with a basilica as a significant feature or component.
-
E.
containsCathedral
Indicates that one entity includes or has within its boundaries a cathedral associated with it.
- 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_69e0c47ef0e48190a50e1bcc43f4b3fd |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1243a2f788190bd4625fa79888696 |
completed | April 28, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6f601f2188190893bcdde0cf58ad6 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:58 p.m.