Triple
T20287030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matthew Heineman |
E509908
|
entity |
| Predicate | directorOf |
P537
|
FINISHED |
| Object | Retrograde |
—
|
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: Retrograde | Statement: [Matthew Heineman, directorOf, Retrograde]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Retrograde Context triple: [Matthew Heineman, directorOf, Retrograde]
-
A.
Retrograde
Retrograde is a song by British electronic musician James Blake, known for its haunting vocals, minimalist production, and emotional intensity.
-
B.
Retrograde
chosen
Retrograde is a 2022 documentary film by Matthew Heineman that chronicles the final months of the U.S. withdrawal from Afghanistan and its impact on Afghan soldiers and civilians.
-
C.
Retrospective
Retrospective is a curated program at the Locarno Film Festival that showcases historically significant or thematically linked films from cinema’s past.
-
D.
Throwback
Throwback is a large-scale abstract steel sculpture by American minimalist artist Tony Smith, known for its geometric form and monumental presence in public space.
-
E.
Retrospecta
Retrospecta is the annual student-edited journal of the Yale School of Architecture, showcasing the school’s design work, research, and critical writing.
- 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_69e0b4c652388190b782cad965e5a098 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e676931fe08190b278d829a745701f |
completed | April 20, 2026, 6:55 p.m. |
Created at: April 16, 2026, 11:07 a.m.