Triple
T6379543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blues for Greeny |
E143545
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object |
Looking for Somebody
"Looking for Somebody" is a blues-rock track by guitarist Gary Moore from his Peter Green tribute album "Blues for Greeny."
|
E589360
|
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: Looking for Somebody | Statement: [Blues for Greeny, hasTrack, Looking for Somebody]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Looking for Somebody Context triple: [Blues for Greeny, hasTrack, Looking for Somebody]
-
A.
Somebody
"Somebody" is a song featured on the album "The Lover in Me."
-
B.
Somebody Loves Me
"Somebody Loves Me" is a 1952 musical biographical film starring Betty Hutton as vaudeville and Broadway star Blossom Seeley.
-
C.
Song for Someone
"Song for Someone" is a reflective, melodic rock ballad by U2 from their 2014 album *Songs of Innocence*, noted for its intimate lyrics and atmospheric sound.
-
D.
Somewhere My Love
"Somewhere My Love" is a popular vocal adaptation of "Lara's Theme" from the film Doctor Zhivago, widely known for its romantic melody and nostalgic lyrics.
-
E.
To Love Somebody
"To Love Somebody" is a classic 1967 soul ballad by the Bee Gees that has become one of their most enduring and frequently covered 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: Looking for Somebody Triple: [Blues for Greeny, hasTrack, Looking for Somebody]
Generated description
"Looking for Somebody" is a blues-rock track by guitarist Gary Moore from his Peter Green tribute album "Blues for Greeny."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Looking for Somebody Target entity description: "Looking for Somebody" is a blues-rock track by guitarist Gary Moore from his Peter Green tribute album "Blues for Greeny."
-
A.
Somebody
"Somebody" is a song featured on the album "The Lover in Me."
-
B.
Somebody Loves Me
"Somebody Loves Me" is a 1952 musical biographical film starring Betty Hutton as vaudeville and Broadway star Blossom Seeley.
-
C.
Song for Someone
"Song for Someone" is a reflective, melodic rock ballad by U2 from their 2014 album *Songs of Innocence*, noted for its intimate lyrics and atmospheric sound.
-
D.
Somewhere My Love
"Somewhere My Love" is a popular vocal adaptation of "Lara's Theme" from the film Doctor Zhivago, widely known for its romantic melody and nostalgic lyrics.
-
E.
To Love Somebody
"To Love Somebody" is a classic 1967 soul ballad by the Bee Gees that has become one of their most enduring and frequently covered 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_69c008d9f4348190ab598a2913259a1c |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0685029488190911fb24c470b6f0d |
completed | March 22, 2026, 10:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c62daf2f408190923d67bd0222d2bb |
completed | March 27, 2026, 7:11 a.m. |
| NEDg | Description generation | batch_69c63321ec688190ae527f6ae9be5791 |
completed | March 27, 2026, 7:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c633e823548190950cc50e360e4ef6 |
completed | March 27, 2026, 7:38 a.m. |
Created at: March 22, 2026, 4:33 p.m.