Triple
T15768700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Paxton |
E382292
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Near Dark |
E268313
|
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: Near Dark | Statement: [William Paxton, notableWork, Near Dark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Near Dark Context triple: [William Paxton, notableWork, Near Dark]
-
A.
Near Dark
chosen
Near Dark is a 1987 neo-Western horror film that blends vampire mythology with gritty Americana and is widely regarded as an influential cult classic.
-
B.
After the Dark
After the Dark is a 2013 philosophical science-fiction thriller film that explores moral dilemmas through a series of apocalyptic thought experiments conducted by a high school philosophy class.
-
C.
Just Before Dark
Just Before Dark is a collection of essays by American writer Jim Harrison that blends memoir, nature writing, food, travel, and literary reflection.
-
D.
Darkest Before Dawn
Darkest Before Dawn is a short film, likely a dramatic or suspenseful work, whose title evokes themes of struggle and hope before a turning point.
-
E.
The Darkest Part
"The Darkest Part" is a song by the American electronic music trio Cheat Codes.
- 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_69d86da09a10819082fe9797b23e4664 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e051951bac8190a7d45f3612c6de72 |
completed | April 16, 2026, 3:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff877a67008190b05f879d05876fd3 |
completed | May 9, 2026, 7:14 p.m. |
Created at: April 10, 2026, 4:47 a.m.