Triple
T9879855
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Homecoming |
E240170
|
entity |
| Predicate | includesSong |
P7178
|
FINISHED |
| Object | Drunk in Love |
E48120
|
NE FINISHED |
How this triple was built (2 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: Drunk in Love | Statement: [Homecoming, includesSong, Drunk in Love]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drunk in Love Context triple: [Homecoming, includesSong, Drunk in Love]
-
A.
Drunk in Love
chosen
"Drunk in Love" is a sultry, trap-influenced R&B song by Beyoncé featuring Jay-Z that became one of her signature hits following its release in 2013.
-
B.
Drunk on Love
"Drunk on Love" is a song by Rihanna from her sixth studio album, blending emotional lyrics with a dance-pop and electronic sound.
-
C.
Marry You
"Marry You" is a catchy pop song by Bruno Mars known for its upbeat, romantic theme about impulsively getting married.
-
D.
Marry You
"Marry You" is a song featured on the collaborative blues album "Riding with the King" by B.B. King and Eric Clapton.
-
E.
Ain't No Thang
"Ain't No Thang" is a track by the hip hop duo Outkast from their influential debut album, showcasing their early Southern rap style and lyrical flair.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca84e8a0788190b9061811d50fd554 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb4146fe881908f9fc553dfca31e1 |
completed | April 2, 2026, 12:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d20d6ec5a081908251e67b575c7c33 |
completed | April 5, 2026, 7:21 a.m. |
Created at: March 30, 2026, 8:37 p.m.