Triple
T31831306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liz Rose |
E812542
|
entity |
| Predicate | wroteSongForArtist |
P44022
|
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: [Liz Rose, wroteSongForArtist, Taylor Swift]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wroteSongForArtist Context triple: [Liz Rose, wroteSongForArtist, Taylor Swift]
-
A.
wroteSongWith
Indicates that two or more entities collaborated in the creation or composition of a song.
-
B.
hasWrittenSongsFor
chosen
Indicates that one entity has composed songs specifically intended to be performed, recorded, or used by another entity.
-
C.
coveredSongBy
Indicates that one musical work is a cover version performed or recorded by an artist of a song originally created or popularized by another artist.
-
D.
hasWrittenLyricsFor
Indicates that one entity is the lyricist who has created the words for a song or musical work performed or associated with another entity.
-
E.
workedOnSongFor
Indicates that one entity contributed work or effort toward creating, producing, or developing a particular song for another entity or purpose.
- 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_69f348ea7ffc8190a2ab43d80277cf59 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6af898f748190a7f3dbb51959233a |
completed | May 3, 2026, 2:14 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:47 p.m.