Triple
T33659312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Junkyard Planet |
E862306
|
entity |
| Predicate | isSetAfterWorkBySameAuthor |
P75851
|
FINISHED |
| Object | Four-Day Planet |
—
|
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: Four-Day Planet | Statement: [Junkyard Planet, isSetAfterWorkBySameAuthor, Four-Day Planet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSetAfterWorkBySameAuthor Context triple: [Junkyard Planet, isSetAfterWorkBySameAuthor, Four-Day Planet]
-
A.
followsWorkBySameAuthors
Indicates that one work comes after and is related to another work created by the same authors.
-
B.
workBySameAuthorAs
Indicates that two works share the same author, i.e., they were created by the same person or entity.
-
C.
precedesWorkBySameCreator
Indicates that one work comes before another work created by the same creator in a sequence or chronology.
-
D.
hasAuthorOfSameWorkAs
Indicates that two authors are related by having written or contributed to the same work.
-
E.
isLaterWorkOfAuthor
chosen
Indicates that one work by an author was created or published after another work by the same author.
- 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_69f349840ba881908e3bfce536aeb92b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fa36f640819098051eff7e5a5787 |
completed | May 3, 2026, 7:33 a.m. |
| PD | Predicate disambiguation | batch_69f6f96dd4c8819093d6a7bd046a9ad5 |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:42 a.m.