Triple
T35387375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarasaland |
E1022824
|
entity |
| Predicate | gameWorldStructure |
P48183
|
FINISHED |
| Object | four kingdoms |
—
|
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: four kingdoms | Statement: [Sarasaland, gameWorldStructure, four kingdoms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gameWorldStructure Context triple: [Sarasaland, gameWorldStructure, four kingdoms]
-
A.
hasWorldStructure
chosen
Indicates that an entity possesses or is characterized by a particular overall world-level organization, framework, or structural configuration.
-
B.
worldType
Indicates the classification or category of world or environment that an entity is associated with.
-
C.
gameElement
Indicates that one entity functions as a component, feature, or part within the structure or mechanics of a game.
-
D.
spawnStructure
Indicates that an entity causes a new structure to be created or instantiated in the environment.
-
E.
geographicalStructure
Indicates a relationship where one entity is a physical geographic feature or formation that characterizes or shapes the spatial nature of another entity or area.
- 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_69f76df34ba48190bd80f0814cdcd540 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f794f87c548190bfef8c623b5cb165 |
completed | May 3, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69f7910770108190bdd39ddb5d304f54 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:03 p.m.