Triple
T32297761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jun’yō |
E825148
|
entity |
| Predicate | islandSuperstructure |
P36734
|
FINISHED |
| Object | starboard side |
—
|
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: starboard side | Statement: [Jun’yō, islandSuperstructure, starboard side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: islandSuperstructure Context triple: [Jun’yō, islandSuperstructure, starboard side]
-
A.
hasIslandSuperstructure
chosen
Indicates that one entity possesses or includes an island-like elevated central structure as a distinct component or feature.
-
B.
superstructureConstructedIn
Indicates that the construction of a superstructure took place at, within, or during a specified location, context, or time.
-
C.
superstructureType
Indicates the specific kind or design category of a structure’s superstructure that an entity possesses or is associated with.
-
D.
islandFort
Indicates a relationship where a fort is located on, or is part of, an island.
-
E.
partOfIsland
Indicates that one entity is a portion or component of an island.
- 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_69f349115304819084ee91d345b6c8aa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bd3d783881909bc4b3335c0bfe1c |
completed | May 3, 2026, 3:13 a.m. |
| PD | Predicate disambiguation | batch_69f6b632cf788190a3d0c08cd026b84b |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:44 a.m.