Triple
T32284303
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jack Snow |
E824782
|
entity |
| Predicate | hasWrittenSeriesEntry |
P161248
|
FINISHED |
| Object | Oz novels |
—
|
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: Oz novels | Statement: [Jack Snow, hasWrittenSeriesEntry, Oz novels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWrittenSeriesEntry Context triple: [Jack Snow, hasWrittenSeriesEntry, Oz novels]
-
A.
hasWrittenForSeries
chosen
Indicates that an entity has authored or contributed written content for a particular series.
-
B.
hasMainSeriesEntry
Indicates that an entity is a primary or canonical installment within a larger series or sequence of related works.
-
C.
hasSeriesRecord
Indicates that one entity maintains a documented record or history of another entity’s participation or performance within a series.
-
D.
hasWrittenRecordsIn
Indicates that an entity has produced or maintains written records in a specified medium, format, or location.
-
E.
hasWrittenFor
Indicates that one entity has created written content (such as articles, stories, or texts) for or on behalf of another entity, typically a publication, organization, or platform.
- 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_69f3490f404081908450db66884f4334 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bcce457c819091b711d6cc66c980 |
completed | May 3, 2026, 3:11 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6cef208190bc5cd43d96127004 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:43 a.m.