Triple
T14080424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lost Highway |
E338850
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Barry Gifford |
E833069
|
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: Barry Gifford | Statement: [Lost Highway, writer, Barry Gifford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Barry Gifford Context triple: [Lost Highway, writer, Barry Gifford]
-
A.
Barry Gifford
chosen
Barry Gifford is an American author and screenwriter best known for his neo-noir novels and for writing the book that inspired David Lynch’s film "Wild at Heart."
-
B.
James Sallis
James Sallis is an American crime and science fiction writer best known for his neo-noir novel "Drive," which was adapted into the 2011 film of the same name.
-
C.
Joe R. Lansdale
Joe R. Lansdale is an American author best known for his crime and horror fiction, particularly the Hap and Leonard novel series.
-
D.
Dan Jewett
Dan Jewett is an American science teacher known for his brief marriage to billionaire philanthropist and novelist MacKenzie Scott.
-
E.
Jeffrey Ford
Jeffrey Ford is a film editor known for his work on major blockbuster movies, including several entries in the Marvel Cinematic Universe.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5f759c81909bfd60ab35b0937b |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb672c08081908e1ff9030745776a |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:21 p.m.