Triple
T21461872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nakatsu Castle |
E529490
|
entity |
| Predicate | demolishedPeriod |
P11080
|
FINISHED |
| Object | Meiji period (most original structures) |
—
|
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: Meiji period (most original structures) | Statement: [Nakatsu Castle, demolishedPeriod, Meiji period (most original structures)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: demolishedPeriod Context triple: [Nakatsu Castle, demolishedPeriod, Meiji period (most original structures)]
-
A.
demolitionPeriod
chosen
Indicates the time span during which the demolition of an entity or structure takes place.
-
B.
demolishedAfter
Indicates that one entity was demolished at a point in time later than the demolition of another entity.
-
C.
demolishedWith
Indicates that one entity was destroyed or torn down using another specified tool, method, or agent.
-
D.
demolishedAfterEvent
Indicates that one entity (typically a structure) was demolished after the occurrence of a specified event.
-
E.
demolishedInDecade
Indicates that something was demolished during a specified decade.
- 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_69e0c458133481908ae8b41a12c4edec |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9ef0c0881908554977df00604a6 |
completed | April 23, 2026, 9:44 a.m. |
| PD | Predicate disambiguation | batch_69e631df1b38819088d3604854e697b4 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:09 p.m.