Triple
T20388024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hold the Dark |
E498007
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Macon Blair |
—
|
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: Macon Blair | Statement: [Hold the Dark, screenwriter, Macon Blair]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Macon Blair Context triple: [Hold the Dark, screenwriter, Macon Blair]
-
A.
Macon Blair
chosen
Macon Blair is an American actor, writer, and director known for his frequent collaborations with filmmaker Jeremy Saulnier and his roles in gritty independent thrillers and dark comedies.
-
B.
Benjamin Keen
Benjamin Keen was a prominent American historian and Latin Americanist known for his influential scholarship on the history and culture of Latin America.
-
C.
Barrett Deems
Barrett Deems was an American jazz drummer best known for his high-energy playing and for performing with Louis Armstrong’s All-Stars in the 1950s.
-
D.
Garret Nagle
Garret Nagle is an Irish environmentalist and academic known for his work in geography and sustainable development.
-
E.
Benjamin Ferris
Benjamin Ferris was a mountaineer known for making the first recorded ascent of Alaska’s Mount Hayes.
- 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6790d9e5881908bde7da9e5e541a0 |
completed | April 20, 2026, 7:05 p.m. |
Created at: April 16, 2026, 11:28 a.m.