Triple
T20869450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | + (album) |
E513851
|
entity |
| Predicate | single |
P3283
|
FINISHED |
| Object |
Drunk
"Drunk" is a song best known as a hit single by English singer-songwriter Ed Sheeran from his debut studio album, +.
|
E1454814
|
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: Drunk | Statement: [+ (album), single, Drunk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drunk Context triple: [+ (album), single, Drunk]
-
A.
Drunk
Drunk is a 2010 Danish drama film directed by Thomas Vinterberg that explores the consequences of a group of teachers testing a theory that maintaining a constant level of alcohol in their blood will improve their lives.
-
B.
Still Drunk
"Still Drunk" is a song by the band Afraid of Ghosts, likely reflecting their indie or alternative rock style and introspective themes.
-
C.
Day Drunk
"Day Drunk" is a pop song co-written by American songwriter Lindy Robbins, known for its catchy melody and relatable, laid-back lyrics about daytime drinking.
-
D.
Driven to Drink
Driven to Drink is a stand-up comedy album by comedian Paul F. Tompkins, showcasing his witty, storytelling-based observational humor.
-
E.
Drunks
Drunks is a 1995 independent drama film that follows a group of recovering alcoholics sharing their stories during an Alcoholics Anonymous meeting.
- 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: Drunk Triple: [+ (album), single, Drunk]
Generated description
"Drunk" is a song best known as a hit single by English singer-songwriter Ed Sheeran from his debut studio album, +.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Drunk Target entity description: "Drunk" is a song best known as a hit single by English singer-songwriter Ed Sheeran from his debut studio album, +.
-
A.
Drunk
Drunk is a 2010 Danish drama film directed by Thomas Vinterberg that explores the consequences of a group of teachers testing a theory that maintaining a constant level of alcohol in their blood will improve their lives.
-
B.
Still Drunk
"Still Drunk" is a song by the band Afraid of Ghosts, likely reflecting their indie or alternative rock style and introspective themes.
-
C.
Day Drunk
"Day Drunk" is a pop song co-written by American songwriter Lindy Robbins, known for its catchy melody and relatable, laid-back lyrics about daytime drinking.
-
D.
Driven to Drink
Driven to Drink is a stand-up comedy album by comedian Paul F. Tompkins, showcasing his witty, storytelling-based observational humor.
-
E.
Drunks
Drunks is a 1995 independent drama film that follows a group of recovering alcoholics sharing their stories during an Alcoholics Anonymous meeting.
- 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_69e0b4f675cc8190b4e745225b62eb66 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c4624ce48190b85e5bb24cf0a305 |
completed | April 21, 2026, 12:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09139a9ef081909585c53823e12ca4 |
completed | May 17, 2026, 1:02 a.m. |
| NEDg | Description generation | batch_6a09144734b0819090901b8e6590222f |
completed | May 17, 2026, 1:05 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0914a0fb4c8190be5d504ff65dfe32 |
completed | May 17, 2026, 1:06 a.m. |
Created at: April 16, 2026, 12:45 p.m.