Triple
T8640211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Live by Night |
E204625
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Live by Night |
E204625
|
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: Live by Night | Statement: [Live by Night, basedOn, Live by Night]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Live by Night Context triple: [Live by Night, basedOn, Live by Night]
-
A.
Live by Night
chosen
Live by Night is a 2016 American crime drama film, based on Dennis Lehane’s novel, that follows a Prohibition-era gangster’s rise in the world of organized crime.
-
B.
Shot at the Night
"Shot at the Night" is a 2013 synth-rock single by American rock band The Killers, produced by M83's Anthony Gonzalez and released as part of their greatest hits album "Direct Hits."
-
C.
Chasing the Night
"Chasing the Night" is a song by the American punk rock band Ramones from their 1984 album *Too Tough to Die*.
-
D.
All Night
"All Night" is a funk-infused hip hop single by American rapper Big Boi, known for its upbeat production and catchy hook from his 2017 album "Boomiverse."
-
E.
All Night
"All Night" is a soulful, uplifting track by Beyoncé from her critically acclaimed visual album "Lemonade," noted for its themes of forgiveness and healing in a relationship.
- 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_69ca834ca1c88190a11ffb0200342fac |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc47944d1c819081f448f14d04bf9d |
completed | March 31, 2026, 10:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cebc340528819085c80b69d6d32a34 |
completed | April 2, 2026, 6:57 p.m. |
Created at: March 30, 2026, 6:28 p.m.