Triple
T5920592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Built to Last |
E131688
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Built to Last (song)
"Built to Last" is a song best known as a 1989 single by the Grateful Dead, featured on their album of the same name.
|
E556297
|
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: Built to Last (song) | Statement: [Built to Last, hasPart, Built to Last (song)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Built to Last (song) Context triple: [Built to Last, hasPart, Built to Last (song)]
-
A.
If It’s Meant to Last
"If It’s Meant to Last" is a song featured on Sheena Easton’s 1988 pop/R&B album *The Lover in Me*.
-
B.
What It Takes
"What It Takes" is a song by the American rock band Aerosmith, released in 1989 as a power ballad from their album "Pump."
-
C.
For What It’s Worth
"For What It’s Worth" is a 1960s protest song by Buffalo Springfield that became an iconic anthem of the era’s social and political unrest.
-
D.
Make It Last
"Make It Last" is a song by the American singer-songwriter CK, known for its smooth production and emotive, melodic style.
-
E.
This Life
"This Life" is a British television drama series that follows the intertwined personal and professional lives of young lawyers sharing a house in London.
- 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: Built to Last (song) Triple: [Built to Last, hasPart, Built to Last (song)]
Generated description
"Built to Last" is a song best known as a 1989 single by the Grateful Dead, featured on their album of the same name.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Built to Last (song) Target entity description: "Built to Last" is a song best known as a 1989 single by the Grateful Dead, featured on their album of the same name.
-
A.
If It’s Meant to Last
"If It’s Meant to Last" is a song featured on Sheena Easton’s 1988 pop/R&B album *The Lover in Me*.
-
B.
What It Takes
"What It Takes" is a song by the American rock band Aerosmith, released in 1989 as a power ballad from their album "Pump."
-
C.
For What It’s Worth
"For What It’s Worth" is a 1960s protest song by Buffalo Springfield that became an iconic anthem of the era’s social and political unrest.
-
D.
Make It Last
"Make It Last" is a song by the American singer-songwriter CK, known for its smooth production and emotive, melodic style.
-
E.
This Life
"This Life" is a British television drama series that follows the intertwined personal and professional lives of young lawyers sharing a house in London.
- 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_69c0085a1ed08190a7e9a8b6323fd680 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c038019ea081908e652d74ff23f076 |
completed | March 22, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0c03a95688190bfd51d7ada1e538f |
completed | March 23, 2026, 4:23 a.m. |
| NEDg | Description generation | batch_69c0c2513aa88190866a59e0b75ef93f |
completed | March 23, 2026, 4:32 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c0c31cd8808190b2f5c7c83f2e4c72 |
completed | March 23, 2026, 4:35 a.m. |
Created at: March 22, 2026, 4 p.m.