Triple
T29789126
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cathédrale Saint-Gatien de Tours |
E756348
|
entity |
| Predicate | previousStyle |
P72530
|
FINISHED |
| Object | Romanesque architecture |
—
|
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 architecture | Statement: [Cathédrale Saint-Gatien de Tours, previousStyle, Romanesque architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousStyle Context triple: [Cathédrale Saint-Gatien de Tours, previousStyle, Romanesque architecture]
-
A.
usedStyle
Indicates that one entity employed or applied a particular style, method, or manner associated with another entity.
-
B.
primaryStyle
Indicates the main or predominant style associated with an entity, distinguishing it from other secondary or supporting styles.
-
C.
previousMode
Indicates that one mode directly precedes another in a sequence or state transition.
-
D.
styleWhenFormer
Indicates a stylistic attribute or manner that applied to an entity during a previous or former state, role, or period.
-
E.
previousArchitecturalStyle
chosen
Indicates that one architectural style directly preceded another in the historical or developmental sequence of a building or design.
- 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_69f22451fb748190bbdbab401280affb |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fd82ed2a4c81908bd7797fbd2e3d08 |
completed | May 8, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fd814cc10481908e4f8123d35a5d0c |
completed | May 8, 2026, 6:23 a.m. |
Created at: April 29, 2026, 5:11 p.m.