Triple
T27635291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Azuchi |
E696453
|
entity |
| Predicate | castleNameOrigin |
P60046
|
FINISHED |
| Object | Azuchi 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: Azuchi Castle | Statement: [Azuchi, castleNameOrigin, Azuchi Castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: castleNameOrigin Context triple: [Azuchi, castleNameOrigin, Azuchi Castle]
-
A.
castleName
chosen
Indicates that an entity has the specified name of a castle.
-
B.
originalCastleFoundedBy
Indicates that an original castle was established or created by a specific person, group, or authority.
-
C.
castleFirstMentioned
Indicates the point in time or context where a particular castle is first recorded or referenced.
-
D.
originalCastleFoundedIn
Indicates the specific year or time period when the original version of a castle was first established or built.
-
E.
fortressNameAtTime
Indicates the name that a particular fortress had during a specified time or 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_69ef5909f3848190805f35b76833e722 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63127da048190aed144e27b34e24e |
completed | May 2, 2026, 5:15 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:23 p.m.