Triple
T26853573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Telmarines |
E676120
|
entity |
| Predicate | relationToOldNarnia |
P198620
|
FINISHED |
| Object | usurped the thrones of the Pevensies |
—
|
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: usurped the thrones of the Pevensies | Statement: [Telmarines, relationToOldNarnia, usurped the thrones of the Pevensies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationToOldNarnia Context triple: [Telmarines, relationToOldNarnia, usurped the thrones of the Pevensies]
-
A.
ageAtFirstVisitToNarnia
Indicates the age a person was when they first visited Narnia.
-
B.
meetsFirstInNarnia
Indicates that one entity first encounters or is introduced to another entity specifically within the context or location of Narnia.
-
C.
relationToShannara
Indicates a relationship or connection that an entity has to the Shannara universe, works, or related elements.
-
D.
relationshipToLittlePrince
Indicates the specific type of personal or emotional connection an entity has to the Little Prince.
-
E.
relationToVonMaur
Indicates a specified type of relationship or association that an entity has with Von Maur.
- 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_69eee9b9d7708190a15d7485709ae981 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69fef8c3f2388190b995ec173512945a |
completed | May 9, 2026, 9:05 a.m. |
| PD | Predicate disambiguation | batch_69fef65975608190960b78d27e806d4f |
completed | May 9, 2026, 8:54 a.m. |
| PDg | Predicate description generation | batch_69fef8c2cdd881908c6f44e4dfa5ffd0 |
completed | May 9, 2026, 9:05 a.m. |
Created at: April 27, 2026, 5:19 a.m.