Triple
T16256887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dark Passage |
E394653
|
entity |
| Predicate | basedOnWorkAuthor |
P2806
|
FINISHED |
| Object | David Goodis |
E824860
|
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: David Goodis | Statement: [Dark Passage, basedOnWorkAuthor, David Goodis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Goodis Context triple: [Dark Passage, basedOnWorkAuthor, David Goodis]
-
A.
David Goodis
chosen
David Goodis was an American noir and hardboiled crime novelist known for his bleak, psychologically driven stories of down-and-out characters.
-
B.
Richard Brody
Richard Brody is an American film critic and author best known for his work at The New Yorker and his writings on French cinema, particularly Jean-Luc Godard.
-
C.
Paul Genzlinger
Paul Genzlinger is a mild-mannered, somewhat awkward music teacher who briefly dates Jessica Day on the TV sitcom "New Girl."
-
D.
Kevin Crowe
Kevin Crowe is a songwriter best known for co-writing the hit track "Young, Wild & Free."
-
E.
Michael Kimmelman
Michael Kimmelman is an American architecture critic and journalist best known for his work at The New York Times.
- 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2459b1624819086bf681075097235 |
completed | April 17, 2026, 2:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a000eebcfe481909822290d3a7b361c |
completed | May 10, 2026, 4:51 a.m. |
Created at: April 10, 2026, 5:04 a.m.