Triple
T25882854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bellavista Fortress |
E652098
|
entity |
| Predicate | functionAfterDemilitarization |
P161242
|
FINISHED |
| Object | museum building |
—
|
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: museum building | Statement: [Bellavista Fortress, functionAfterDemilitarization, museum building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: functionAfterDemilitarization Context triple: [Bellavista Fortress, functionAfterDemilitarization, museum building]
-
A.
functionAfterSuppression
Indicates that one function or process occurs only after another has been suppressed or inhibited.
-
B.
functionAfterConversion
Indicates that one function or behavior occurs as a result of, or is valid only after, a specified conversion has taken place.
-
C.
integratedAfter
Indicates that one entity was incorporated, merged, or combined into another only after a specified entity, event, or version had already been integrated.
-
D.
classAfter
Indicates that one class or course occurs later in time or sequence than another class or course.
-
E.
functionAfterReformation
Indicates that one function or role exists or is performed in the state or period following a process of reformation or reform.
- 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_69e7ab3b92cc81908febd90317862647 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6135293908190809e255bf6334760 |
completed | May 2, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_69f611a9272881909093360472be832c |
completed | May 2, 2026, 3 p.m. |
| PDg | Predicate description generation | batch_69f6125e54e0819088ee33a20efcc9e6 |
completed | May 2, 2026, 3:03 p.m. |
Created at: April 22, 2026, 8:17 a.m.