Triple
T36254643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Dunes |
E891899
|
entity |
| Predicate | hasSequelRelationshipType |
P1961
|
FINISHED |
| Object | subsequent installment |
—
|
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: subsequent installment | Statement: [The Dunes, hasSequelRelationshipType, subsequent installment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSequelRelationshipType Context triple: [The Dunes, hasSequelRelationshipType, subsequent installment]
-
A.
hasSequelType
Indicates that one work has a sequel of a specified type or category in relation to another work.
-
B.
hasSequelOrRelated
Indicates that one work follows, continues, or is otherwise narratively or thematically related to another work.
-
C.
hasSequel
chosen
Indicates that one work is followed by another work that continues its story, timeline, or thematic development.
-
D.
hasSequelRole
Indicates that an entity plays a corresponding or continued role in a sequel to an earlier work.
-
E.
hasSequelLikeCycle
Indicates that a work is part of a sequence where sequels form a cycle, such that following the sequel relationships eventually leads back to the original work.
- 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_69f76e4599108190811532e707d6bc2c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a004b6ad4248190b402a0d01b0ebf83 |
completed | May 10, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_6a004ae736b881908a0efed8f63f982e |
completed | May 10, 2026, 9:07 a.m. |
Created at: May 3, 2026, 4:09 p.m.