Triple
T9390489
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bad (album) |
E226014
|
entity |
| Predicate | track |
P17929
|
FINISHED |
| Object |
Liberian Girl
"Liberian Girl" is a smooth, romantic R&B song by Michael Jackson, celebrated for its Afro-Caribbean influences and lush production.
|
E795820
|
NE FINISHED |
How this triple was built (4 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: Liberian Girl | Statement: [Bad (album), track, Liberian Girl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liberian Girl Context triple: [Bad (album), track, Liberian Girl]
-
A.
White Girl
"White Girl" is a 2016 independent drama film about a college student’s reckless summer of drugs and obsession in New York City, in which Justin Bartha appears.
-
B.
A Girl in Black
A Girl in Black is a 1956 Greek drama film, set on a remote island, that explores themes of social oppression and forbidden love.
-
C.
A Negra
A Negra is a seminal modernist painting by Brazilian artist Tarsila do Amaral that explores Afro-Brazilian identity through bold forms and vibrant colors.
-
D.
Voodoo Song
"Voodoo Song" is an early version and working title of J Balvin and Willy William’s global reggaeton hit "Mi Gente."
-
E.
Ya Mama
"Ya Mama" is a track by British DJ and producer Fatboy Slim, featured on his 2000 electronic/big beat album *Halfway Between the Gutter and the Stars*.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Liberian Girl Triple: [Bad (album), track, Liberian Girl]
Generated description
"Liberian Girl" is a smooth, romantic R&B song by Michael Jackson, celebrated for its Afro-Caribbean influences and lush production.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Liberian Girl Target entity description: "Liberian Girl" is a smooth, romantic R&B song by Michael Jackson, celebrated for its Afro-Caribbean influences and lush production.
-
A.
White Girl
"White Girl" is a 2016 independent drama film about a college student’s reckless summer of drugs and obsession in New York City, in which Justin Bartha appears.
-
B.
A Girl in Black
A Girl in Black is a 1956 Greek drama film, set on a remote island, that explores themes of social oppression and forbidden love.
-
C.
A Negra
A Negra is a seminal modernist painting by Brazilian artist Tarsila do Amaral that explores Afro-Brazilian identity through bold forms and vibrant colors.
-
D.
Voodoo Song
"Voodoo Song" is an early version and working title of J Balvin and Willy William’s global reggaeton hit "Mi Gente."
-
E.
Ya Mama
"Ya Mama" is a track by British DJ and producer Fatboy Slim, featured on his 2000 electronic/big beat album *Halfway Between the Gutter and the Stars*.
- F. None of above. chosen
Provenance (5 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_69ca842f7e3481908bf5bcf52e032dbd |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd510d7a9c8190a74ccdb5478dedc9 |
completed | April 1, 2026, 5:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d100f86bac8190a26ab156f24455bb |
completed | April 4, 2026, 12:15 p.m. |
| NEDg | Description generation | batch_69d10156670c8190b61ef6231c2e78d2 |
completed | April 4, 2026, 12:17 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d10235f46c8190ba8eeb9382649f62 |
completed | April 4, 2026, 12:21 p.m. |
Created at: March 30, 2026, 7:45 p.m.