Triple
T21528793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freddie Thorp |
E531173
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | To Dream |
—
|
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: To Dream | Statement: [Freddie Thorp, appearedIn, To Dream]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: To Dream Context triple: [Freddie Thorp, appearedIn, To Dream]
-
A.
To Dream
chosen
"To Dream" is an independent British coming-of-age drama film featuring Freddie Thorp in a prominent role.
-
B.
In a Dream
"In a Dream" is a hip-hop track by rapper Hodgy Beats, known for its introspective lyrics and atmospheric production.
-
C.
One Dream
One Dream is a component of the Beijing 2008 Olympic Games slogan "One World, One Dream," expressing a shared aspiration for unity and harmony among people worldwide.
-
D.
A Dream
"A Dream" is a 1980s R&B ballad by Bunny DeBarge, best known for its lush harmonies and for being heavily sampled in later hip-hop and R&B tracks.
-
E.
Some Dream
"Some Dream" is a song by Japanese musician and producer Perfume Genius from his critically acclaimed 2020 album "Set My Heart on Fire Immediately."
- 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_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee8852e68c8190a5341c9f75081382 |
completed | April 26, 2026, 9:49 p.m. |
Created at: April 16, 2026, 6:27 p.m.