Triple
T14043310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scars on Broadway |
E337897
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object | Opeth |
E543450
|
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: Opeth | Statement: [Scars on Broadway, associatedAct, Opeth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Opeth Context triple: [Scars on Broadway, associatedAct, Opeth]
-
A.
Opeth
chosen
Opeth is a Swedish progressive metal band renowned for blending death metal, progressive rock, and acoustic elements into complex, atmospheric compositions.
-
B.
DragonForce
DragonForce is a British power metal band renowned for its extremely fast guitar work and epic, video game–inspired sound.
-
C.
Gojira
Gojira is a French progressive death metal band renowned for its technical musicianship, environmental themes, and influential presence in the modern metal scene.
-
D.
Gojira
Gojira is the original Japanese name for Godzilla, the iconic giant monster from Japanese cinema and pop culture.
-
E.
Edguy
Edguy is a German power metal band known for its melodic, fast-paced songs and humorous, theatrical style led by vocalist Tobias Sammet.
- 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de312b94308190bd0961f5bc719c7b |
completed | April 14, 2026, 12:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbc33f79a88190999978d7f34632cd |
completed | May 6, 2026, 10:39 p.m. |
Created at: April 9, 2026, 10:20 p.m.