Triple
T2011038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taylor Swift |
E43686
|
entity |
| Predicate | notableSong |
P4
|
FINISHED |
| Object |
Bad Blood
"Bad Blood" is a 2015 pop song by Taylor Swift, best known for its high-profile remix featuring Kendrick Lamar and its star-studded, cinematic music video.
|
E227286
|
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: Bad Blood | Statement: [Taylor Swift, notableSong, Bad Blood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bad Blood Context triple: [Taylor Swift, notableSong, Bad Blood]
-
A.
Wrecking Ball
Wrecking Ball is a 2012 studio album by American rock musician Bruce Springsteen that blends rock, folk, and gospel influences to address themes of economic hardship and social justice.
-
B.
So Cruel
"So Cruel" is a moody, emotionally charged song by U2 from their critically acclaimed 1991 album Achtung Baby.
-
C.
Letter to You
"Letter to You" is a 2020 studio album by Bruce Springsteen, recorded with the E Street Band and noted for its reflective themes on aging, mortality, and the power of rock music.
-
D.
Bring Me Down
"Bring Me Down" is a song by Kanye West featuring Brandy from his critically acclaimed 2005 album *Late Registration*.
-
E.
Come As You Are
"Come As You Are" is a song from the 2001 R&B album "Afrodisiac" by American singer Brandy.
- 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: Bad Blood Triple: [Taylor Swift, notableSong, Bad Blood]
Generated description
"Bad Blood" is a 2015 pop song by Taylor Swift, best known for its high-profile remix featuring Kendrick Lamar and its star-studded, cinematic music video.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bad Blood Target entity description: "Bad Blood" is a 2015 pop song by Taylor Swift, best known for its high-profile remix featuring Kendrick Lamar and its star-studded, cinematic music video.
-
A.
Wrecking Ball
Wrecking Ball is a 2012 studio album by American rock musician Bruce Springsteen that blends rock, folk, and gospel influences to address themes of economic hardship and social justice.
-
B.
So Cruel
"So Cruel" is a moody, emotionally charged song by U2 from their critically acclaimed 1991 album Achtung Baby.
-
C.
Letter to You
"Letter to You" is a 2020 studio album by Bruce Springsteen, recorded with the E Street Band and noted for its reflective themes on aging, mortality, and the power of rock music.
-
D.
Bring Me Down
"Bring Me Down" is a song by Kanye West featuring Brandy from his critically acclaimed 2005 album *Late Registration*.
-
E.
Come As You Are
"Come As You Are" is a song from the 2001 R&B album "Afrodisiac" by American singer Brandy.
- 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_69a88716e9f08190946313fdc949e3cf |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8b150a8819096c919465fd91ab5 |
completed | March 7, 2026, 5:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae0ae85ed48190adc75fd17b17f6c9 |
completed | March 8, 2026, 11:48 p.m. |
| NEDg | Description generation | batch_69ae0b76f0fc8190bb5f40689ee7f8fe |
completed | March 8, 2026, 11:51 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae0c586bd88190ae23e84291d2fe81 |
completed | March 8, 2026, 11:55 p.m. |
Created at: March 4, 2026, 7:37 p.m.