Triple
T31370848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nils Sjöberg |
E800156
|
entity |
| Predicate | hiddenAuthorshipFor |
P116978
|
FINISHED |
| Object | Taylor Swift |
—
|
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: Taylor Swift | Statement: [Nils Sjöberg, hiddenAuthorshipFor, Taylor Swift]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hiddenAuthorshipFor Context triple: [Nils Sjöberg, hiddenAuthorshipFor, Taylor Swift]
-
A.
hiddenAt
Indicates that one entity is concealed or stored at a specific location or within another entity.
-
B.
hiddenIn
Indicates that one entity is concealed within, behind, or inside another entity so that it is not readily visible or apparent.
-
C.
authorshipInitially
Indicates that an entity is the original or first author/creator of another entity before any subsequent authorship changes or contributions.
-
D.
hasUnknownAuthor
Indicates that the author of the entity is not known or cannot be identified.
-
E.
purportedAuthors
chosen
Indicates that certain entities are claimed or alleged to be the authors of another entity, without asserting that the authorship is definitively verified.
- 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_69f224e6b7448190ac6bf97ad7364160 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69f89a7f881909b2eaca8904ba555 |
completed | May 3, 2026, 1:06 a.m. |
| PD | Predicate disambiguation | batch_69f69d1d25e88190a7f57d323574da90 |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:18 p.m.