Triple
T20579066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bad Guy |
E505304
|
entity |
| Predicate | followedBy |
P78
|
FINISHED |
| Object | Bury a Friend |
—
|
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: Bury a Friend | Statement: [Bad Guy, followedBy, Bury a Friend]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bury a Friend Context triple: [Bad Guy, followedBy, Bury a Friend]
-
A.
Bury a Friend
chosen
"Bury a Friend" is a dark, minimalist electropop song by Billie Eilish that helped define her eerie aesthetic and propelled her rise to global fame.
-
B.
Bury Me
"Bury Me" is a country song by Dwight Yoakam, featured on his debut album "Guitars, Cadillacs, Etc., Etc."
-
C.
Bury Me Next to You
"Bury Me Next to You" is a song featured on the album *In Another Life*.
-
D.
Kill Your Friends
Kill Your Friends is a darkly comic British film (based on John Niven’s novel) that satirizes the ruthless 1990s music industry through the violent, ambition-fueled rise of an A&R executive.
-
E.
Deadly Friend
Deadly Friend is a 1986 science fiction horror film that blends robotics and supernatural elements, directed by genre filmmaker Wes Craven.
- 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_69e0b4b721588190993ac7b0a9be2736 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a90cc22c8190969e3a21ae92f1c9 |
completed | April 20, 2026, 10:30 p.m. |
Created at: April 16, 2026, 11:39 a.m.