Triple
T38444675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sinéad Lohan |
E906611
|
entity |
| Predicate | hasSongFeaturedOn |
P20452
|
FINISHED |
| Object | Joan Baez album Gone From Danger |
—
|
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: Joan Baez album Gone From Danger | Statement: [Sinéad Lohan, hasSongFeaturedOn, Joan Baez album Gone From Danger]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSongFeaturedOn Context triple: [Sinéad Lohan, hasSongFeaturedOn, Joan Baez album Gone From Danger]
-
A.
hasFeaturedArtist
Indicates that an entity (such as a song or track) includes another artist who appears as a featured performer.
-
B.
hasSong
chosen
Indicates that one entity possesses, features, or includes a particular song.
-
C.
featuredOnSong
Indicates that an entity (such as an artist) appears as a guest or secondary contributor on a particular song.
-
D.
hasSongAbout
Indicates that one entity has created, features, or is associated with a song whose subject or theme is about another entity.
-
E.
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.
- 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_69f76e72878c8190a692836c8b01b58b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fe08d2b2e48190ac7be6d62d4a44a3 |
completed | May 8, 2026, 4:01 p.m. |
| PD | Predicate disambiguation | batch_69fe06cd3af08190ae25de0dc0cdd573 |
completed | May 8, 2026, 3:52 p.m. |
Created at: May 3, 2026, 4:31 p.m.