Triple
T30599670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Celduin |
E778871
|
entity |
| Predicate | cartography |
P95647
|
FINISHED |
| Object | marked on Tolkien’s maps of Wilderland |
—
|
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: marked on Tolkien’s maps of Wilderland | Statement: [Celduin, cartography, marked on Tolkien’s maps of Wilderland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cartography Context triple: [Celduin, cartography, marked on Tolkien’s maps of Wilderland]
-
A.
cartographicWork
chosen
Indicates a relationship where one entity is a cartographic work (such as a map or chart) that represents geographic information about another entity.
-
B.
cartographyBy
Indicates that one entity is the creator or producer of the cartographic work (such as a map or chart) associated with another entity.
-
C.
cartographicUse
Indicates the way in which something is used or intended to be used within a cartographic or map-making context.
-
D.
cartographicInnovation
Indicates the introduction or use of new methods, techniques, or technologies in map-making or geographic representation.
-
E.
cartographicContent
Indicates that the resource contains or is associated with map-related or cartographic information.
- 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_69f224a1570c8190a85d3ac330479a79 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f689b0dbe08190aeacfb2d5386b46d |
completed | May 2, 2026, 11:33 p.m. |
| PD | Predicate disambiguation | batch_69f67e448a9c8190b591374d98799fe3 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:25 p.m.