Triple
T14605666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Electric Light |
E342822
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Sugar Drunk High |
E1108597
|
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: Sugar Drunk High | Statement: [Electric Light, hasPart, Sugar Drunk High]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sugar Drunk High Context triple: [Electric Light, hasPart, Sugar Drunk High]
-
A.
Sugar Drunk High
chosen
Sugar Drunk High is a track featured on the album "Electric Light" by English singer-songwriter James Bay.
-
B.
Sugarhigh
"Sugarhigh" is a high-energy rock song best known for its climactic performance scene in the 1995 cult film *Empire Records*.
-
C.
Drunk in the Morning
"Drunk in the Morning" is a pop song best known as one of the early hits associated with Danish singer-songwriter Lukas Graham, co-written and produced by Morten Ristorp.
-
D.
Junkies on a High
"Junkies on a High" is a song by Green Day from their 2020 album "Father of All Motherfuckers," blending garage rock and alternative punk influences.
-
E.
Gettin' High
"Gettin' High" is a hip hop song by Ol' Dirty Bastard from his 1999 album "Nigga Please," showcasing his eccentric style and offbeat delivery.
- 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_69d822dec68081908c2553145c4051dc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb44bf67c8190b4c48a7715f9443e |
completed | April 14, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fda91d05e48190ac945e381d6d5dd9 |
completed | May 8, 2026, 9:13 a.m. |
Created at: April 10, 2026, 1:25 a.m.