Triple
T26484696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toyama Castle |
E664788
|
entity |
| Predicate | mainKeepStatus |
P115733
|
FINISHED |
| Object | reconstructed |
—
|
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: reconstructed | Statement: [Toyama Castle, mainKeepStatus, reconstructed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainKeepStatus Context triple: [Toyama Castle, mainKeepStatus, reconstructed]
-
A.
currentKeepStatus
Indicates the present retention or preservation state currently assigned to an entity.
-
B.
controlStatus
Indicates that one entity has a particular level, state, or condition of control over another entity or process.
-
C.
maintenanceStatus
Indicates the current state or condition of an entity with respect to its maintenance activities, such as whether it is pending, in progress, completed, or overdue.
-
D.
mainKeepRebuilt
chosen
Indicates that the primary defensive tower or central stronghold of a structure has been reconstructed or restored after damage or destruction.
-
E.
modernStatus
Indicates the current or contemporary condition, classification, or standing of an entity in the present time.
- 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_69ee883bc85481909885f92415cbce33 |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f612fe5494819094d4efbeefd82049 |
completed | May 2, 2026, 3:06 p.m. |
| PD | Predicate disambiguation | batch_69f602d5c8808190a1fdbebd6f0981e8 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 27, 2026, 12:29 a.m.