Triple
T32136321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harima Province |
E820771
|
entity |
| Predicate | hadMajorCastle |
P22469
|
FINISHED |
| Object | Himeji Castle |
—
|
NE NERFINISHED |
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: Himeji Castle | Statement: [Harima Province, hadMajorCastle, Himeji Castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadMajorCastle Context triple: [Harima Province, hadMajorCastle, Himeji Castle]
-
A.
hasFamousCastle
Indicates that an entity possesses or is the location of a castle that is widely recognized or renowned.
-
B.
hasCastle
chosen
Indicates that one entity possesses, controls, or contains a castle.
-
C.
hasCastleRemains
Indicates that one entity possesses or contains the remaining structures or ruins of a castle associated with it.
-
D.
eraOfMainCastle
Indicates the historical period or era during which the main castle associated with an entity was built, used, or most prominent.
-
E.
castleBuilt
Indicates that a castle has been constructed or established, typically by a specific agent or during a particular time period.
- 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_69f349039e0c819091c7a7d322e3f46d |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b9a9bc4c8190a88918fc4f91136a |
completed | May 3, 2026, 2:57 a.m. |
| PD | Predicate disambiguation | batch_69f6b6293188819080d5041ca0adb969 |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:30 a.m.