Triple
T22912914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Facelift |
E568650
|
entity |
| Predicate | notableSingle |
P3283
|
FINISHED |
| Object | Sea of Sorrow |
—
|
NE NERFINISHED |
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: Sea of Sorrow | Statement: [Facelift, notableSingle, Sea of Sorrow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sea of Sorrow Context triple: [Facelift, notableSingle, Sea of Sorrow]
-
A.
Sea of Sorrow
chosen
"Sea of Sorrow" is a dark, heavy grunge track by Alice in Chains, featured on their influential 1990 album *Facelift*.
-
B.
Ensiferum
Ensiferum is a Finnish folk metal band known for blending melodic death metal with epic, Viking-themed lyrics and symphonic elements.
-
C.
Krallice
Krallice is an American experimental black metal band known for its complex, highly technical compositions and involvement in the New York avant‑metal scene.
-
D.
Underoath
Underoath is an American Christian metalcore band known for their intense sound, emotionally charged lyrics, and influential role in the 2000s post-hardcore and metalcore scenes.
-
E.
Orange Order
The Orange Order is a Protestant fraternal organization originating in Ireland, known for promoting unionism and organizing parades, particularly in Northern Ireland.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2458d90c88190a58cead4e781ca6a |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18075a0048190bd150e2badeeb7c2 |
completed | April 29, 2026, 3:52 a.m. |
Created at: April 17, 2026, 3:42 p.m.