Triple
T35293253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karnwasten |
E1019286
|
entity |
| Predicate | mapMarkerType |
P149332
|
FINISHED |
| Object | public dungeon 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: public dungeon icon | Statement: [Karnwasten, mapMarkerType, public dungeon icon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mapMarkerType Context triple: [Karnwasten, mapMarkerType, public dungeon icon]
-
A.
mapSymbol
Indicates a correspondence where one symbol is used to represent, stand for, or denote another element within a mapping or representation system.
-
B.
mapSymbolStandard
Indicates that a map symbol conforms to, or is defined according to, a particular cartographic standard or specification.
-
C.
mapsType
Indicates that one entity serves as a mapping whose values or outputs are of the specified type.
-
D.
mappingType
Indicates the specific kind or category of correspondence established between two related elements or representations.
-
E.
markerFormat
chosen
Indicates the specific style or format in which a marker (such as a symbol, label, or annotation) is presented or rendered in relation to something it marks.
- 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_69f76de7eedc8190a3bdc64ebbc05b42 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7901ae65c819092f17f92d7b2e561 |
completed | May 3, 2026, 6:12 p.m. |
| PD | Predicate disambiguation | batch_69f78e2f52e08190a77661223a96c601 |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:03 p.m.