Triple
T19379676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Faery Isle of Janjira |
E484763
|
entity |
| Predicate | worldbuildingFunction |
P135746
|
FINISHED |
| Object | adds magical atmosphere to The Broken Wing |
—
|
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: adds magical atmosphere to The Broken Wing | Statement: [The Faery Isle of Janjira, worldbuildingFunction, adds magical atmosphere to The Broken Wing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worldbuildingFunction Context triple: [The Faery Isle of Janjira, worldbuildingFunction, adds magical atmosphere to The Broken Wing]
-
A.
worldType
Indicates the classification or category of world or environment that an entity is associated with.
-
B.
worldName
Indicates that an entity has or is associated with a specific world’s name.
-
C.
fictionalPlanet
Indicates that the subject is a planet that exists only in fiction or imagination, not in the real universe.
-
D.
fictionalUniverseLocation
Indicates that one entity is a location or setting within the fictional universe to which the other entity belongs or in which it takes place.
-
E.
fictionalPlaceType
Indicates that a place is a fictional location and specifies what type or category of fictional place it is.
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61a5e8e7081908bed3eee1eef4de2 |
completed | April 20, 2026, 12:21 p.m. |
| PD | Predicate disambiguation | batch_69e4fd54f8e48190956e73dd8969164a |
completed | April 19, 2026, 4:05 p.m. |
| PDg | Predicate description generation | batch_69e5004c23308190a087b7941a90725f |
completed | April 19, 2026, 4:18 p.m. |
Created at: April 10, 2026, 1:35 p.m.