Triple
T28728267
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iga Ueno Castle |
E730284
|
entity |
| Predicate | wasBuiltAs |
P8196
|
FINISHED |
| Object | military stronghold |
—
|
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: military stronghold | Statement: [Iga Ueno Castle, wasBuiltAs, military stronghold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasBuiltAs Context triple: [Iga Ueno Castle, wasBuiltAs, military stronghold]
-
A.
wasBuilt
Indicates that one entity constructed, created, or assembled another entity, typically at a specific time or over a period.
-
B.
isBuiltFor
chosen
Indicates that one entity is specifically designed, intended, or optimized to serve, support, or accommodate another entity or purpose.
-
C.
builtOn
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
D.
builtFrom
Indicates that one entity is constructed, composed, or formed using another entity as its material, component, or source.
-
E.
builtAsPartOf
Indicates that one entity was constructed as a component or subset of a larger, encompassing entity or project.
- 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_69f043e91fe48190b73bcd8e08d433e0 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f6576569bc8190b0eb1f0fde785c14 |
completed | May 2, 2026, 7:58 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 5:57 a.m.