Triple
T34453223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donjon de Rouen |
E884431
|
entity |
| Predicate | isSurvivingPartOf |
P22068
|
FINISHED |
| Object | former castle of Rouen |
—
|
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: former castle of Rouen | Statement: [Donjon de Rouen, isSurvivingPartOf, former castle of Rouen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSurvivingPartOf Context triple: [Donjon de Rouen, isSurvivingPartOf, former castle of Rouen]
-
A.
isSurvivorOf
Indicates that one entity has lived through, endured, or remained alive after a particular event, condition, or harmful circumstance involving another entity.
-
B.
structurePartOf
Indicates that one structure is a constituent or component of a larger, encompassing structure.
-
C.
isOnlyPartOf
Indicates that an entity is a component exclusively of a specific whole and not of any other whole.
-
D.
containedPartOf
Indicates that one entity is physically or logically included within and forms a part of another entity.
-
E.
isYoungerRemnantOf
chosen
Indicates that one entity is the surviving, younger portion or successor of another entity that existed earlier and has largely disappeared or transformed.
- 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_69f349c607688190b553539d14901a35 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7197526a08190bf800fcc3948122e |
completed | May 3, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69f71824431081908d9685d2462ea242 |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 2 a.m.