Triple
T36738049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Abyssinians |
E907535
|
entity |
| Predicate | songTitleLanguage |
P58593
|
FINISHED |
| Object |
Satta Massagana is partly in Amharic
"Satta Massagana is partly in Amharic" is a multilingual reggae song by The Abyssinians that blends English with Amharic lyrics and Rastafarian spiritual themes.
|
E2197736
|
NE FINISHED |
How this triple was built (3 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: Satta Massagana is partly in Amharic | Statement: [The Abyssinians, songTitleLanguage, Satta Massagana is partly in Amharic]
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: Satta Massagana is partly in Amharic Triple: [The Abyssinians, songTitleLanguage, Satta Massagana is partly in Amharic]
Generated description
"Satta Massagana is partly in Amharic" is a multilingual reggae song by The Abyssinians that blends English with Amharic lyrics and Rastafarian spiritual themes.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: songTitleLanguage Context triple: [The Abyssinians, songTitleLanguage, Satta Massagana is partly in Amharic]
-
A.
languageOfTrackTitles
chosen
Indicates the language in which the titles of the tracks are written or presented.
-
B.
lyricsLanguage
Indicates the language in which the lyrics of a song or musical work are written or performed.
-
C.
languageOfMusic
Indicates that a specified language is used in, associated with, or characteristic of a particular piece of music or musical work.
-
D.
titleInLanguage
Indicates that a specific title or name is expressed in a particular language.
-
E.
originalLanguageOfSourceSong
Indicates that a given language is the original language in which a particular source song was created or first written.
- F. None of above.
Provenance (6 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_69f76e75aa6881909b844d00a3888ee5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c9f5a8848190ba956ff27f44e396 |
completed | May 3, 2026, 10:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3c172da0788190afaa121b4d5e6607 |
completed | June 24, 2026, 5:43 p.m. |
| NEDg | Description generation | batch_6a3c17d595a08190b8e006b7aca8421a |
completed | June 24, 2026, 5:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a3c6ca9620c819080418d4a40073577 |
completed | June 24, 2026, 11:47 p.m. |
| PD | Predicate disambiguation | batch_69f7c8999a348190abc1895eaa6e036d |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.