Triple
T6377151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shaggy |
E143493
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Angel
"Angel" is a romantic reggae fusion song by Shaggy, featuring Rayvon, best known for its smooth melody and chart-topping success in the early 2000s.
|
E587673
|
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: Angel | Statement: [Shaggy, notableWork, Angel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angel Context triple: [Shaggy, notableWork, Angel]
-
A.
Angel
"Angel" is a 1937 romantic comedy film directed by Ernst Lubitsch, known for its sophisticated wit and starring Marlene Dietrich, Herbert Marshall, and Melvyn Douglas.
-
B.
Angel
Angel is a winged mutant warrior in the X-Men universe, often depicted with metallic feathered wings and a conflicted, tormented nature.
-
C.
Angel
Angel is a given name used across various cultures, often associated with spiritual or celestial connotations.
-
D.
Angel
"Angel" is a song by the American rock band Aerosmith, best known as a power ballad from their 1987 album *Permanent Vacation*.
-
E.
Angel
Angel is a vibrant district in central London known for its bustling high street, cultural venues, and lively dining and nightlife scene.
- 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: Angel Triple: [Shaggy, notableWork, Angel]
Generated description
"Angel" is a romantic reggae fusion song by Shaggy, featuring Rayvon, best known for its smooth melody and chart-topping success in the early 2000s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Angel Target entity description: "Angel" is a romantic reggae fusion song by Shaggy, featuring Rayvon, best known for its smooth melody and chart-topping success in the early 2000s.
-
A.
Angel
"Angel" is a song by the American rock band Aerosmith, best known as a power ballad from their 1987 album *Permanent Vacation*.
-
B.
Angel
"Angel" is a melancholic, piano-driven ballad by Canadian singer-songwriter Sarah McLachlan, widely known for its emotional resonance and use in various charitable and memorial contexts.
-
C.
Angel
"Angel" is a 1937 romantic comedy film directed by Ernst Lubitsch, known for its sophisticated wit and starring Marlene Dietrich, Herbert Marshall, and Melvyn Douglas.
-
D.
Angel
Angel is a vibrant district in central London known for its bustling high street, cultural venues, and lively dining and nightlife scene.
-
E.
Angel
Angel is an American supernatural drama television series set in the Buffy the Vampire Slayer universe, following a vampire with a soul seeking redemption in Los Angeles.
- 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_69c008d9f4348190ab598a2913259a1c |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0683d7af881908d66d5230e1bfcb6 |
completed | March 22, 2026, 10:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c62da390c081908690ec716aed8fea |
completed | March 27, 2026, 7:11 a.m. |
| NEDg | Description generation | batch_69c62dfff4e08190a4491fdef022acb6 |
completed | March 27, 2026, 7:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c62e7c07a88190a366ff23605cb161 |
completed | March 27, 2026, 7:15 a.m. |
Created at: March 22, 2026, 4:33 p.m.