Triple
T12641151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ninomaru Garden |
E301899
|
entity |
| Predicate | overlooksFrom |
P1323
|
FINISHED |
| Object | reception rooms of Ninomaru Palace |
—
|
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: reception rooms of Ninomaru Palace | Statement: [Ninomaru Garden, overlooksFrom, reception rooms of Ninomaru Palace]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: overlooksFrom Context triple: [Ninomaru Garden, overlooksFrom, reception rooms of Ninomaru Palace]
-
A.
overlooks
chosen
Indicates that one entity has a view toward or looks out over another entity, typically from a higher or adjacent position.
-
B.
hasNumberOfOverlooks
Indicates the specific count of overlooks (such as viewing points or vantage spots) associated with an entity.
-
C.
overlooksForPromotion
Indicates that an entity responsible for promotions fails to select or consider another entity for advancement despite potential eligibility.
-
D.
viewOver
Indicates that one entity has a visual perspective overlooking or facing another entity, typically providing a vantage point onto it.
-
E.
observesFrom
Indicates that one entity watches, monitors, or takes note of another entity from a particular vantage point or location.
- 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_69d7bdec9f9c8190b4bac675b7588211 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d961ae493481908f82e0d05dce20bd |
completed | April 10, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69d960b47130819097e1162ed4fc993a |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:17 p.m.