Triple
T35421623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donut Plains Castle |
E1023809
|
entity |
| Predicate | hasWorldMapIcon |
P197146
|
FINISHED |
| Object | castle icon |
—
|
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: castle icon | Statement: [Donut Plains Castle, hasWorldMapIcon, castle icon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWorldMapIcon Context triple: [Donut Plains Castle, hasWorldMapIcon, castle icon]
-
A.
hasWorldMap
Indicates that one entity possesses, includes, or is associated with a representation of the entire world’s geography.
-
B.
hasWorldMapNodeType
Indicates that something is associated with a specific type or category of node within a world map structure.
-
C.
hasWorldMapConnectionTo
Indicates that one location is directly connected to another on a world map, such as by a route, link, or navigable path.
-
D.
hasMaps
Indicates that one entity possesses, includes, or provides access to one or more maps associated with another entity.
-
E.
hasWorld
Indicates that an entity possesses, is associated with, or encompasses a particular world or global context.
- F. None of above. chosen
Provenance (4 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_69f76df6704081909900c60be10d5849 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fe78e545888190a239af1a84280fa0 |
completed | May 8, 2026, 11:59 p.m. |
| PD | Predicate disambiguation | batch_69fe7842742081908043eb950ed69f92 |
completed | May 8, 2026, 11:56 p.m. |
| PDg | Predicate description generation | batch_69fe78e35e6c8190b8b440777912f64e |
completed | May 8, 2026, 11:59 p.m. |
Created at: May 3, 2026, 4:03 p.m.