Triple
T33252646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mikawa region |
E851289
|
entity |
| Predicate | hasHistoricCastleTown |
P87637
|
FINISHED |
| Object | Okazaki |
—
|
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: Okazaki | Statement: [Mikawa region, hasHistoricCastleTown, Okazaki]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHistoricCastleTown Context triple: [Mikawa region, hasHistoricCastleTown, Okazaki]
-
A.
hasCastleTownHistory
chosen
Indicates that an entity has a historical association with a castle town, such as originating from, being located in, or significantly shaped by one.
-
B.
containsHistoricTown
Indicates that one entity geographically includes or encompasses a town that has recognized historical significance.
-
C.
hasHistoricTownRights
Indicates that an entity possesses officially granted historic town rights, typically conferring a traditional legal or municipal status as a town.
-
D.
hasMajorCastleTown
Indicates that a place possesses a principal or most important castle town associated with it.
-
E.
hasHistoricCathedralCity
Indicates that one entity is historically recognized as a cathedral city associated with or belonging to another entity.
- 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_69f34963135c819084e7f1d483421f00 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fec4cffed08190b5e5e7cc0c87493e |
completed | May 9, 2026, 5:23 a.m. |
| PD | Predicate disambiguation | batch_69fec2ea7fe08190bd751b39515f69d1 |
completed | May 9, 2026, 5:15 a.m. |
Created at: May 1, 2026, 1:31 a.m.