Triple
T8764017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shattered Heart |
E208280
|
entity |
| Predicate | performer |
P1363
|
FINISHED |
| Object | Matt Walst |
E803688
|
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: Matt Walst | Statement: [Shattered Heart, performer, Matt Walst]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Walst Context triple: [Shattered Heart, performer, Matt Walst]
-
A.
Matt Walst
chosen
Matt Walst is a Canadian rock singer best known as the lead vocalist of the band Three Days Grace.
-
B.
Brad Walst
Brad Walst is a Canadian musician best known as the bassist and a founding member of the rock band Three Days Grace.
-
C.
Matt Wolpert
Matt Wolpert is a television writer and producer best known for co-creating the alternate-history space drama series "For All Mankind."
-
D.
Matt Wertz
Matt Wertz is an American singer-songwriter known for his melodic pop and acoustic-driven music, often associated with the contemporary Christian and indie pop scenes.
-
E.
Matt Luber
Matt Luber is a film producer best known for his work on the action-thriller movie "Into the Blue."
- 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_69ca835df7e08190ac875664cca8f9ca |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5dfdef9881908a7f079d87e8e338 |
completed | March 31, 2026, 11:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d189c795d48190ba80739d07bc899c |
completed | April 4, 2026, 9:59 p.m. |
Created at: March 30, 2026, 6:40 p.m.