Triple
T12944902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rokovoko |
E309734
|
entity |
| Predicate | hasFictionalGeography |
P98586
|
FINISHED |
| Object | isolated island |
—
|
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: isolated island | Statement: [Rokovoko, hasFictionalGeography, isolated island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalGeography Context triple: [Rokovoko, hasFictionalGeography, isolated island]
-
A.
hasFictionalLocation
Indicates that an entity is associated with, set in, or takes place within a location that exists only in fiction rather than in the real world.
-
B.
hasBranchInFictionalLocation
Indicates that an organization maintains a branch, office, or presence within a fictional or imaginary location.
-
C.
belongsToFictionalContinent
Indicates that something is located on, associated with, or a part of a specific fictional continent within an imagined world.
-
D.
fictionalGeographicRegion
chosen
Indicates that a geographic region exists only in fiction or imagination rather than in the real world.
-
E.
locatedInFictionalCountry
Indicates that an entity exists or is situated within a country that is fictional rather than real.
- 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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97db69f548190a1a693bc0d6c191a |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 5:43 p.m.