Triple
T7217779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamaudun Mausoleum |
E150178
|
entity |
| Predicate | toponymy |
P74345
|
FINISHED |
| Object | name means “royal mausoleum” in Okinawan language |
—
|
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: name means “royal mausoleum” in Okinawan language | Statement: [Tamaudun Mausoleum, toponymy, name means “royal mausoleum” in Okinawan language]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: toponymy Context triple: [Tamaudun Mausoleum, toponymy, name means “royal mausoleum” in Okinawan language]
-
A.
hasToponymy
Indicates a relationship where one entity possesses or is associated with the system, study, or set of place names (toponyms) of another entity.
-
B.
isToponymic
Indicates that something is related to or derived from a place name (a toponym).
-
C.
toponymLiteralMeaning
chosen
Indicates the literal or etymological meaning of a place name (toponym), describing what the name directly translates to or signifies.
-
D.
toponymSourceFor
Indicates that one entity serves as the origin, basis, or source from which another entity’s place name (toponym) is derived.
-
E.
hasToponymicForm
Indicates that one entity is a toponymic (place-name-based) form or variant derived from another entity.
- 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_69c687effb44819092b95d07d0368c9f |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6e99170d88190b1aef326a7d81134 |
completed | March 27, 2026, 8:33 p.m. |
| PD | Predicate disambiguation | batch_69c6e75f84e481909e7866186ae80cff |
completed | March 27, 2026, 8:23 p.m. |
Created at: March 27, 2026, 2:53 p.m.