Triple
T20623434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dig Up Her Bones |
E506757
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object | Michale Graves |
—
|
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: Michale Graves | Statement: [Dig Up Her Bones, composer, Michale Graves]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michale Graves Context triple: [Dig Up Her Bones, composer, Michale Graves]
-
A.
Michale Graves
chosen
Michale Graves is an American punk rock singer best known as the lead vocalist for the Misfits during their 1990s reformation era.
-
B.
Michael Richter
Michael Richter is a relatively common personal name shared by multiple individuals across fields such as sports, academia, and the arts.
-
C.
Robert Gorman
Robert Gorman is an American former child actor best known for his role in the 1993 family comedy film "Mr. Nanny."
-
D.
Mike Gill
Mike Gill is a New Zealand mountaineer known for pioneering Himalayan ascents, including the first ascent of Thamserku.
-
E.
Michael Graves
Michael Graves was an influential American architect and designer renowned for his colorful, playful postmodern buildings and widely popular product designs.
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6abe3177c8190ad1b2ca8b1e0a560 |
completed | April 20, 2026, 10:42 p.m. |
Created at: April 16, 2026, 11:42 a.m.