Triple
T32971702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Let's Just Say It Wasn't Pretty |
E843535
|
entity |
| Predicate | previousWorkByAuthor |
P198266
|
FINISHED |
| Object | Then Again |
—
|
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: Then Again | Statement: [Let's Just Say It Wasn't Pretty, previousWorkByAuthor, Then Again]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousWorkByAuthor Context triple: [Let's Just Say It Wasn't Pretty, previousWorkByAuthor, Then Again]
-
A.
previousWorkByArtist
Indicates that the related work was created earlier by the same artist as the current or reference work.
-
B.
previousWorkByProducer
Indicates that a work was created earlier by the same producer responsible for another referenced work.
-
C.
authorOfPreviousWork
Indicates that one entity is the creator or writer of an earlier work referenced or built upon by another entity.
-
D.
revisitsWorkByAuthor
Indicates that an entity returns to and engages again with a work created by a particular author.
-
E.
publishedWorksBy
Indicates that one entity has created works that have been made publicly available by another entity (such as an author’s works published by a publisher).
- 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_69f3494b9fc48190bb61c955ba471275 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fed6da0390819096b88ef4714b144e |
completed | May 9, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69fed53517d081909966f31707625f1a |
completed | May 9, 2026, 6:33 a.m. |
| PDg | Predicate description generation | batch_69fed6d90f2081909cd21e5e973a6b89 |
completed | May 9, 2026, 6:40 a.m. |
Created at: May 1, 2026, 1:21 a.m.