Triple
T18356021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | P.S. I Love You |
E439797
|
entity |
| Predicate | catalogNumberUKSingle |
P34455
|
FINISHED |
| Object | Parlophone R 4949 |
—
|
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: Parlophone R 4949 | Statement: [P.S. I Love You, catalogNumberUKSingle, Parlophone R 4949]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: catalogNumberUKSingle Context triple: [P.S. I Love You, catalogNumberUKSingle, Parlophone R 4949]
-
A.
thirdUKNumberOneSingle
Indicates that the subject entity is the third single by the artist to reach number one on the UK singles chart.
-
B.
secondUKNumberOneSingle
Indicates that the subject is the artist or act whose second UK number one single is the object.
-
C.
isFirstUKNumberOneSingleFor
Indicates that a particular song is the first UK number-one single achieved by a given artist or group.
-
D.
firstNumberOneSingleForArtistInUK
Indicates that the artist has exactly one single that reached number one on the charts in the UK.
-
E.
recordLabelCatalogNumber
chosen
Indicates the catalog or identification number assigned to a release by a record label.
- 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_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e516d69ae081908a36e7c3559a0694 |
completed | April 19, 2026, 5:54 p.m. |
| PD | Predicate disambiguation | batch_69e44fed3fdc81908f4ed6a81db42416 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:37 a.m.