Triple
T15570777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Death Cure |
E374232
|
entity |
| Predicate | filmAdaptationDirector |
P255
|
FINISHED |
| Object | Wes Ball |
E374233
|
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: Wes Ball | Statement: [The Death Cure, filmAdaptationDirector, Wes Ball]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wes Ball Context triple: [The Death Cure, filmAdaptationDirector, Wes Ball]
-
A.
Wes Ball
chosen
Wes Ball is an American film director best known for helming the Maze Runner science-fiction film series.
-
B.
Travis Knight
Travis Knight is an American animator, film director, and CEO of the stop-motion animation studio Laika, known for directing films such as "Kubo and the Two Strings."
-
C.
Zach Helm
Zach Helm is an American screenwriter, director, and producer best known for writing the metafictional film "Stranger Than Fiction."
-
D.
Jon Hurwitz
Jon Hurwitz is an American screenwriter, producer, and director best known as the co-creator of the Harold & Kumar film series and the Netflix series Cobra Kai.
-
E.
Michael Gracey
Michael Gracey is an Australian filmmaker and visual effects artist best known for directing the hit musical film "The Greatest Showman."
- 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e1de0488190b3639fc25f79d343 |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff56c231e0819083d6032eb21114b2 |
completed | May 9, 2026, 3:46 p.m. |
Created at: April 10, 2026, 4:10 a.m.