Triple
T23581929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint-Germain-l’Auxerrois Church |
E582227
|
entity |
| Predicate | naveConstruction |
P152798
|
FINISHED |
| Object | 15th century |
—
|
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: 15th century | Statement: [Saint-Germain-l’Auxerrois Church, naveConstruction, 15th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: naveConstruction Context triple: [Saint-Germain-l’Auxerrois Church, naveConstruction, 15th century]
-
A.
naveType
Indicates the architectural or structural type or style of a building’s nave in relation to that nave.
-
B.
numberOfNaves
Indicates the specific count of naves (longitudinal sections) that a building, typically a church, possesses.
-
C.
shipDesigned
Indicates that one entity is responsible for designing or creating the design of a ship associated with another entity.
-
D.
naveLength
Indicates the length measurement of a building’s nave, typically from the entrance to the chancel or crossing.
-
E.
hullConstruction
Indicates the process or activity of building, assembling, or forming the main body (hull) of a vessel or similar structure.
- 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_69e248f8d8248190acd5aee77f0d1709 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b02cf4e0819094ff4e406cda270d |
completed | April 29, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f118c96a0081908a8ac98ef7e7e60c |
completed | April 28, 2026, 8:30 p.m. |
| PDg | Predicate description generation | batch_69f121cc494081908c987adfcde89b0e |
completed | April 28, 2026, 9:08 p.m. |
Created at: April 17, 2026, 6:40 p.m.