Triple
T4034664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pure Souls |
E83798
|
entity |
| Predicate | lyricist |
P1360
|
FINISHED |
| Object | Shenseea |
E252762
|
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: Shenseea | Statement: [Pure Souls, lyricist, Shenseea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shenseea Context triple: [Pure Souls, lyricist, Shenseea]
-
A.
Shenseea
chosen
Shenseea is a Jamaican dancehall and reggae fusion artist known for her energetic performances, genre-blending hits, and high-profile collaborations in contemporary Caribbean music.
-
B.
Chase & Status
Chase & Status are a British electronic music production and DJ duo known for their influential work in drum and bass and dubstep.
-
C.
Oxmo Puccino
Oxmo Puccino is a French-Malian rapper and lyricist renowned for his poetic, introspective storytelling and influential role in the French hip-hop scene.
-
D.
Labrinth
Labrinth is a British singer, songwriter, and record producer known for his genre-blending pop, R&B, and electronic music, as well as his work on hit singles and acclaimed soundtracks like HBO's "Euphoria."
-
E.
The Ting Tings
The Ting Tings are an English indie pop duo known for their catchy, danceable hits like "That's Not My Name" and "Shut Up and Let Me Go."
- 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_69aed92f7cf0819098e0539bdcc3767f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb11d92481909aaebbc250ff45b9 |
completed | March 9, 2026, 4:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b56b4a54c48190ae8abe0188b9738b |
completed | March 14, 2026, 2:06 p.m. |
Created at: March 9, 2026, 3:36 p.m.