Triple
T24527530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunpu Castle |
E606706
|
entity |
| Predicate | belongsToCastleType |
P43483
|
FINISHED |
| Object | hirajiro (flatland castle) |
—
|
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: hirajiro (flatland castle) | Statement: [Sunpu Castle, belongsToCastleType, hirajiro (flatland castle)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToCastleType Context triple: [Sunpu Castle, belongsToCastleType, hirajiro (flatland castle)]
-
A.
hasCastleType
chosen
Indicates that an entity is associated with, characterized by, or classified as a specific type of castle.
-
B.
hasCastle
Indicates that one entity possesses, controls, or contains a castle.
-
C.
hasCastleFeature
Indicates that an entity possesses or includes a specific architectural or structural feature of a castle.
-
D.
belongsToBuildingType
Indicates that something is classified as being of a particular building type.
-
E.
hasCastleUse
Indicates that something is used or designated for a particular castle-related purpose or function.
- 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_69e2c4c85778819085f5da9af3569ad5 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b0ca8081908d931aec560eae56 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:25 a.m.