Triple
T16672250
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Smoke & Mirrors |
E405132
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object |
Here Tomorrow Gone Today
"Here Tomorrow Gone Today" is a song by the American rock band Smoke & Mirrors.
|
E1226918
|
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: Here Tomorrow Gone Today | Statement: [Smoke & Mirrors, hasTrack, Here Tomorrow Gone Today]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Here Tomorrow Gone Today Context triple: [Smoke & Mirrors, hasTrack, Here Tomorrow Gone Today]
-
A.
Come Tomorrow
"Come Tomorrow" is a song from Rumble Doll, the 1993 solo debut album by American singer-songwriter Patti Scialfa.
-
B.
Come Tomorrow
Come Tomorrow is a 2018 studio album by American rock group Dave Matthews Band, known for its blend of rock, jazz, and folk influences and for debuting at number one on the Billboard 200.
-
C.
Live Tomorrow
"Live Tomorrow" is a pop song by Swedish singer-songwriter Laleh, known for its introspective lyrics and emotive vocal performance.
-
D.
Yesterday to Tomorrow
"Yesterday to Tomorrow" is a song featured on Audioslave's 2005 rock album *Out of Exile*.
-
E.
Gone Tomorrow
"Gone Tomorrow" is a crime thriller novel by Mick Herron, best known as an early entry in his body of work that showcases his sharp, character-driven storytelling.
- 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: Here Tomorrow Gone Today Triple: [Smoke & Mirrors, hasTrack, Here Tomorrow Gone Today]
Generated description
"Here Tomorrow Gone Today" is a song by the American rock band Smoke & Mirrors.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Here Tomorrow Gone Today Target entity description: "Here Tomorrow Gone Today" is a song by the American rock band Smoke & Mirrors.
-
A.
Come Tomorrow
Come Tomorrow is a 2018 studio album by American rock group Dave Matthews Band, known for its blend of rock, jazz, and folk influences and for debuting at number one on the Billboard 200.
-
B.
Come Tomorrow
"Come Tomorrow" is a song from Rumble Doll, the 1993 solo debut album by American singer-songwriter Patti Scialfa.
-
C.
Live Tomorrow
"Live Tomorrow" is a pop song by Swedish singer-songwriter Laleh, known for its introspective lyrics and emotive vocal performance.
-
D.
Yesterday to Tomorrow
"Yesterday to Tomorrow" is a song featured on Audioslave's 2005 rock album *Out of Exile*.
-
E.
Gone Tomorrow
"Gone Tomorrow" is a crime thriller novel by Mick Herron, best known as an early entry in his body of work that showcases his sharp, character-driven storytelling.
- 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_69d8838b5fbc81908c6575c132b82e80 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37ca175088190a0435422e13278c2 |
completed | April 18, 2026, 12:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a008a3916508190bd5edd91310ddb5a |
completed | May 10, 2026, 1:38 p.m. |
| NEDg | Description generation | batch_6a008b001c988190b0ddec3be0ed6fd0 |
completed | May 10, 2026, 1:41 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a008b9a8b6481909df37edcecdd292c |
completed | May 10, 2026, 1:43 p.m. |
Created at: April 10, 2026, 5:19 a.m.