Triple
T33748279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beverly of Graustark |
E864759
|
entity |
| Predicate | hasFictionalMonarchy |
P143705
|
FINISHED |
| Object | Kingdom of Graustark |
—
|
NE NERFINISHED |
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: Kingdom of Graustark | Statement: [Beverly of Graustark, hasFictionalMonarchy, Kingdom of Graustark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalMonarchy Context triple: [Beverly of Graustark, hasFictionalMonarchy, Kingdom of Graustark]
-
A.
appearsInFictionalMonarchy
Indicates that an entity is featured as part of a fictional monarchy within a narrative work.
-
B.
countryOfFictionalMonarchy
Indicates the real-world country in which a fictional monarchy is located or to which it belongs.
-
C.
fictionalRoyalHouse
chosen
Indicates that an entity belongs to, is associated with, or is a member of a royal house that exists only in fiction.
-
D.
fictionalKingdom
Indicates that an entity is a kingdom that exists only in fiction or imaginative works, rather than in real-world history.
-
E.
hasMonarchFrom
Indicates that a political entity is ruled by, or has as its monarch, a specific individual from a given time or context.
- 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_69f3498c35f881909df279ae4270f831 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff46afe7e481908f2862ed11c88db2 |
completed | May 9, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69ff45e9151881909c444a655e852165 |
completed | May 9, 2026, 2:34 p.m. |
Created at: May 1, 2026, 1:45 a.m.