Triple
T18084030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Born Free |
E432782
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object |
Purple Sky
"Purple Sky" is a song featured on the soundtrack of the 2010 animated film "Born Free."
|
E1305027
|
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: Purple Sky | Statement: [Born Free, hasTrack, Purple Sky]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Purple Sky Context triple: [Born Free, hasTrack, Purple Sky]
-
A.
Blue Miles
Blue Miles is the frequent-flyer loyalty program of Pakistani airline Airblue, offering passengers the ability to earn and redeem miles for flights and related benefits.
-
B.
Blue Sky
"Blue Sky" is a melodic, country-influenced rock song by the Allman Brothers Band, celebrated for its dual guitar harmonies and uplifting, improvisational feel.
-
C.
Blue Sky
Blue Sky is a 1994 drama film starring Jessica Lange as the troubled wife of a U.S. Army officer, a role that earned her an Academy Award for Best Actress.
-
D.
Wake Up in the Sky
"Wake Up in the Sky" is a melodic hip-hop single by Gucci Mane featuring Bruno Mars and Kodak Black, known for its smooth, luxurious vibe and chart success.
-
E.
Mr. Blue Sky
"Mr. Blue Sky" is a 1977 upbeat, orchestral rock song by Electric Light Orchestra, widely recognized as one of the band’s signature and most enduring hits.
- 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: Purple Sky Triple: [Born Free, hasTrack, Purple Sky]
Generated description
"Purple Sky" is a song featured on the soundtrack of the 2010 animated film "Born Free."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Purple Sky Target entity description: "Purple Sky" is a song featured on the soundtrack of the 2010 animated film "Born Free."
-
A.
Blue Miles
Blue Miles is the frequent-flyer loyalty program of Pakistani airline Airblue, offering passengers the ability to earn and redeem miles for flights and related benefits.
-
B.
Blue Sky
"Blue Sky" is a melodic, country-influenced rock song by the Allman Brothers Band, celebrated for its dual guitar harmonies and uplifting, improvisational feel.
-
C.
Blue Sky
Blue Sky is a 1994 drama film starring Jessica Lange as the troubled wife of a U.S. Army officer, a role that earned her an Academy Award for Best Actress.
-
D.
Wake Up in the Sky
"Wake Up in the Sky" is a melodic hip-hop single by Gucci Mane featuring Bruno Mars and Kodak Black, known for its smooth, luxurious vibe and chart success.
-
E.
Mr. Blue Sky
"Mr. Blue Sky" is a 1977 upbeat, orchestral rock song by Electric Light Orchestra, widely recognized as one of the band’s signature and most enduring hits.
- 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_69d8b907d05c819083cc3bd6021089e6 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4d9fcdbec819085752e7605ae7772 |
completed | April 19, 2026, 1:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a035d8f11a48190bc123bd65e203905 |
completed | May 12, 2026, 5:04 p.m. |
| NEDg | Description generation | batch_6a03621f4c7481909fb37fa4421404b6 |
completed | May 12, 2026, 5:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0362d876288190800eb73d0d566842 |
completed | May 12, 2026, 5:26 p.m. |
Created at: April 10, 2026, 10:27 a.m.