Triple
T17042848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | To Whom It May Concern |
E413487
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
So Lovely
"So Lovely" is a song featured on the album *To Whom It May Concern*.
|
E1247592
|
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: So Lovely | Statement: [To Whom It May Concern, hasPart, So Lovely]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: So Lovely Context triple: [To Whom It May Concern, hasPart, So Lovely]
-
A.
So Beautiful
"So Beautiful" is a soulful R&B song written and produced by Carvin Haggins, known for its heartfelt lyrics and smooth, emotive vocal delivery.
-
B.
She's So Lovely
"She's So Lovely" is a 1997 romantic drama film directed by Nick Cassavetes, based on a script by his father John Cassavetes and starring Sean Penn and Robin Wright.
-
C.
Sweet and Lovely
"Sweet and Lovely" is a popular jazz and pop standard from the early 1930s that has been widely recorded by numerous vocalists and instrumentalists.
-
D.
Sweet Love
"Sweet Love" is a track featured on Wizkid’s 2017 album *Sounds from the Other Side*, blending Afrobeats with smooth R&B influences.
-
E.
Lovely to Look At
Lovely to Look At is a 1952 MGM musical film, loosely based on the stage musical Roberta, featuring lavish Technicolor production numbers and classic Jerome Kern songs.
- 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: So Lovely Triple: [To Whom It May Concern, hasPart, So Lovely]
Generated description
"So Lovely" is a song featured on the album *To Whom It May Concern*.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: So Lovely Target entity description: "So Lovely" is a song featured on the album *To Whom It May Concern*.
-
A.
So Beautiful
"So Beautiful" is a soulful R&B song written and produced by Carvin Haggins, known for its heartfelt lyrics and smooth, emotive vocal delivery.
-
B.
She's So Lovely
"She's So Lovely" is a 1997 romantic drama film directed by Nick Cassavetes, based on a script by his father John Cassavetes and starring Sean Penn and Robin Wright.
-
C.
Sweet and Lovely
"Sweet and Lovely" is a popular jazz and pop standard from the early 1930s that has been widely recorded by numerous vocalists and instrumentalists.
-
D.
Sweet Love
"Sweet Love" is a track featured on Wizkid’s 2017 album *Sounds from the Other Side*, blending Afrobeats with smooth R&B influences.
-
E.
Lovely to Look At
Lovely to Look At is a 1952 MGM musical film, loosely based on the stage musical Roberta, featuring lavish Technicolor production numbers and classic Jerome Kern songs.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d8f870c0819087e4a20083d761f1 |
completed | April 18, 2026, 7:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01233a7e44819096f71f5007b4450f |
completed | May 11, 2026, 12:30 a.m. |
| NEDg | Description generation | batch_6a01241510048190ae1c459873f8a587 |
completed | May 11, 2026, 12:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0124e389908190b2ee3121be2c9383 |
completed | May 11, 2026, 12:37 a.m. |
Created at: April 10, 2026, 5:33 a.m.