Triple
T26070477
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berserker Death |
E657528
|
entity |
| Predicate | workInAuthorSeries |
P159914
|
FINISHED |
| Object | Berserker stories by Fred Saberhagen |
—
|
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: Berserker stories by Fred Saberhagen | Statement: [Berserker Death, workInAuthorSeries, Berserker stories by Fred Saberhagen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workInAuthorSeries Context triple: [Berserker Death, workInAuthorSeries, Berserker stories by Fred Saberhagen]
-
A.
relatedWorkSeriesAuthor
Indicates that an author is associated with a work that is part of the same series or a related series as another work.
-
B.
seriesAuthor
Indicates that an entity is the author or primary creator of a series (such as a book, comic, or media series).
-
C.
workOfAuthorOf
Indicates that one entity is a work (such as a book, article, or artwork) created by the author associated with another entity.
-
D.
workOfAuthorWho
Indicates that one entity is a work (such as a book, article, or artwork) created by another entity who is its author.
-
E.
notableWorkSeries
Indicates that a work is part of a series for which the subject is notably known or recognized.
- 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_69ee5bbe539081909efc7f9dd7c1b53c |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f606ca69b08190977693fd1f8e8ae4 |
completed | May 2, 2026, 2:14 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
| PDg | Predicate description generation | batch_69f5f6b32a8881909baa0db57b80d56a |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 26, 2026, 7:28 p.m.