Triple
T9995770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cliff Curtis |
E197197
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Blow |
E349295
|
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: Blow | Statement: [Cliff Curtis, notableWork, Blow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blow Context triple: [Cliff Curtis, notableWork, Blow]
-
A.
Blow
chosen
Blow is a 2001 crime drama film that chronicles the rise and fall of American cocaine smuggler George Jung within the 1970s–1980s drug trade.
-
B.
Blow
"Blow" is a disco-funk inspired song by Beyoncé, known for its sensual lyrics, retro production, and vibrant roller-disco themed visuals.
-
C.
Blow Out
Blow Out is a 1981 neo-noir political thriller film directed by Brian De Palma, known for its suspenseful blend of conspiracy, sound design, and psychological tension.
-
D.
Black Book
Black Book is a 2006 Dutch World War II thriller film directed by Paul Verhoeven, acclaimed for its gripping espionage story and moral complexity.
-
E.
Killing Them Softly
Killing Them Softly is a 2012 American crime film, based on George V. Higgins' novel "Cogan's Trade," that follows a hitman investigating a heist on a mob-protected poker game.
- 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcb9af6a88190942cc4991bd373c1 |
completed | April 2, 2026, 1:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d258336ab8819098d4878b8c106d86 |
completed | April 5, 2026, 12:40 p.m. |
Created at: March 30, 2026, 8:50 p.m.