Triple
T19913463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1989 (Ryan Adams album) |
E478604
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object | Bad Blood |
—
|
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: Bad Blood | Statement: [1989 (Ryan Adams album), hasTrack, Bad Blood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bad Blood Context triple: [1989 (Ryan Adams album), hasTrack, Bad Blood]
-
A.
Bad Blood
"Bad Blood" is a 2015 pop song by Taylor Swift, best known for its high-profile remix featuring Kendrick Lamar and its star-studded, cinematic music video.
-
B.
Bad Blood
chosen
"Bad Blood" is a song recorded by the American R&B/rock and roll group The Coasters.
-
C.
Bad Blood (film)
Bad Blood is a thriller film featuring Carly Chaikin in a prominent role, centered on dark family secrets and deadly consequences.
-
D.
Hollywood’s Bleeding
Hollywood’s Bleeding is Post Malone’s third studio album, blending hip hop, pop, and rock influences and featuring hit singles like “Circles” and “Goodbyes.”
-
E.
Drain You
"Drain You" is a grunge song by Nirvana, featured on their landmark 1991 album Nevermind and noted for its dynamic shifts and surreal lyrics.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e520682081909892916424699bd5 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659917fdc8190bf29bfdab0fe8f85 |
completed | April 20, 2026, 4:51 p.m. |
Created at: April 10, 2026, 1:53 p.m.