Triple
T37471636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winter Queen |
E931166
|
entity |
| Predicate | associatedRealmType |
P68775
|
FINISHED |
| Object | afterlife for nature spirits |
—
|
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: afterlife for nature spirits | Statement: [Winter Queen, associatedRealmType, afterlife for nature spirits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedRealmType Context triple: [Winter Queen, associatedRealmType, afterlife for nature spirits]
-
A.
associatedWithRealm
Indicates a relationship where an entity is linked or connected to a particular realm, domain, or sphere of influence.
-
B.
realmType
Indicates the classification or category of a realm, specifying what kind or type of realm it is.
-
C.
parentRealm
Indicates that one realm serves as the immediate higher-level or containing realm in which another realm is situated.
-
D.
realmTypeConnected
Indicates that two realm types are linked or associated in a way that allows interaction, transition, or shared properties between them.
-
E.
realmAssociatedWith
chosen
Indicates an association or connection between an entity and a particular realm, domain, or sphere with which it is linked or to which it pertains.
- 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_69f76ec2af148190897d101070d7f415 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a13a1308190a202df66f4781855 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:17 p.m.