Triple
T22892302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beach House |
E568071
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Bloom |
—
|
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: Bloom | Statement: [Beach House, notableWork, Bloom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bloom Context triple: [Beach House, notableWork, Bloom]
-
A.
Bloom
Bloom is a common English and Jewish surname borne by numerous notable figures in literature, academia, and the arts.
-
B.
Bloom
Bloom is a large open-access multilingual language model developed by the BigScience research workshop for text generation and understanding tasks.
-
C.
Bloom
chosen
Bloom is the second studio album by Australian singer-songwriter Troye Sivan, known for its lush pop production and explorations of queer love and self-discovery.
-
D.
Bloom
Bloom is a film production company known for financing and producing independent and international feature films.
-
E.
Bloom Innocent
Bloom Innocent is a 2019 studio album by British singer-songwriter and producer Fink, blending atmospheric folk, blues, and electronic influences.
- 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_69e2458c23ec81908fa2570692c6614f |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f17fc66dbc81909b31c068d7f2c531 |
completed | April 29, 2026, 3:49 a.m. |
Created at: April 17, 2026, 3:40 p.m.