Triple
T6882647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TLC |
E158835
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Unpretty
"Unpretty" is a 1999 R&B song by American girl group TLC that addresses themes of self-esteem, body image, and societal beauty standards.
|
E625132
|
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: Unpretty | Statement: [TLC, notableWork, Unpretty]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Unpretty Context triple: [TLC, notableWork, Unpretty]
-
A.
Ugly Truth
"Ugly Truth" is a song by the American rock band Soundgarden from their 1989 album Louder Than Love.
-
B.
Nasty Girl
"Nasty Girl" is a 2004 hip hop single by rapper Nelly, known for its club-oriented sound and inclusion on his album "Sweat."
-
C.
Beautiful Mess
"Beautiful Mess" is a popular country song by American band Diamond Rio, known for its catchy melody and portrayal of love's chaotic charm.
-
D.
Cry Pretty
"Cry Pretty" is a 2018 country-pop studio album by American singer Carrie Underwood, noted for its emotional themes and powerful vocal performances.
-
E.
Everything I'm Not
"Everything I'm Not" is a pop-rock single by Australian duo The Veronicas, known for its catchy melody and lyrics about self-acceptance and rejecting a toxic relationship.
- 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: Unpretty Triple: [TLC, notableWork, Unpretty]
Generated description
"Unpretty" is a 1999 R&B song by American girl group TLC that addresses themes of self-esteem, body image, and societal beauty standards.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Unpretty Target entity description: "Unpretty" is a 1999 R&B song by American girl group TLC that addresses themes of self-esteem, body image, and societal beauty standards.
-
A.
Ugly Truth
"Ugly Truth" is a song by the American rock band Soundgarden from their 1989 album Louder Than Love.
-
B.
Nasty Girl
"Nasty Girl" is a 2004 hip hop single by rapper Nelly, known for its club-oriented sound and inclusion on his album "Sweat."
-
C.
Beautiful Mess
"Beautiful Mess" is a popular country song by American band Diamond Rio, known for its catchy melody and portrayal of love's chaotic charm.
-
D.
Cry Pretty
"Cry Pretty" is a 2018 country-pop studio album by American singer Carrie Underwood, noted for its emotional themes and powerful vocal performances.
-
E.
Everything I'm Not
"Everything I'm Not" is a pop-rock single by Australian duo The Veronicas, known for its catchy melody and lyrics about self-acceptance and rejecting a toxic relationship.
- 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_69c688342f6c8190ad7eea6ba262db99 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d8e90c9481908d00634f67fa71f8 |
completed | March 27, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c742d00d848190a4bab9800a7e3888 |
completed | March 28, 2026, 2:54 a.m. |
| NEDg | Description generation | batch_69c74389290c8190a9a2a3675c31316b |
completed | March 28, 2026, 2:57 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7444e57a881908808a4bd96505048 |
completed | March 28, 2026, 3 a.m. |
Created at: March 27, 2026, 2:23 p.m.