Triple
T19238058
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Church of the Saintes Maries de la Mer |
E481053
|
entity |
| Predicate | fortifiedFeature |
P72483
|
FINISHED |
| Object | crenellated roof |
—
|
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: crenellated roof | Statement: [Church of the Saintes Maries de la Mer, fortifiedFeature, crenellated roof]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fortifiedFeature Context triple: [Church of the Saintes Maries de la Mer, fortifiedFeature, crenellated roof]
-
A.
fortifiedBuilding
Indicates that a building is strengthened or reinforced for defense against attacks or intrusions.
-
B.
fortifiedIn
Indicates that one entity has been strengthened, reinforced, or protected within or by another entity (such as a structure, location, or medium).
-
C.
isFortifiedWith
chosen
Indicates that one entity has been strengthened, enriched, or supplemented by the addition of another entity.
-
D.
fortifiedSite
Indicates a site that has been strengthened or defended with protective structures or measures against attack.
-
E.
fortificationCommanded
Indicates that one entity holds authority over and directs the defense or operation of a particular fortification or fortified structure.
- 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_69d8e8ccb8f48190ad420098e74fb1db |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5faee7324819090a4c56147cb0bf5 |
completed | April 20, 2026, 10:07 a.m. |
| PD | Predicate disambiguation | batch_69e4dcfae6f081909cc173cf71a5005c |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:26 p.m.