Triple
T1678680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Nighy |
E36288
|
entity |
| Predicate | workIn |
P1527
|
FINISHED |
| Object | Shaun of the Dead |
E190450
|
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: Shaun of the Dead | Statement: [Bill Nighy, workIn, Shaun of the Dead]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shaun of the Dead Context triple: [Bill Nighy, workIn, Shaun of the Dead]
-
A.
Shaun of the Dead
chosen
Shaun of the Dead is a 2004 British horror-comedy film that parodies zombie movies while following an underachiever’s chaotic attempt to save his loved ones during a zombie apocalypse.
-
B.
Withnail & I
Withnail & I is a 1987 British black comedy cult film about two out-of-work actors on a disastrous holiday in the English countryside.
-
C.
Zombieland
Zombieland is a 2009 horror-comedy film about a group of survivors navigating a zombie apocalypse with a mix of humor, gore, and quirky survival rules.
-
D.
House of 1000 Corpses
House of 1000 Corpses is a 2003 horror film directed by Rob Zombie that follows a group of young travelers who encounter a sadistic family of killers in rural America.
-
E.
The Cabin in the Woods
The Cabin in the Woods is a 2012 meta-horror film that deconstructs and satirizes classic horror movie tropes through a self-aware, genre-bending storyline.
- 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_69a886139ed081909af0940aa9313512 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa625f7e1081909c3c4fe76625783a |
completed | March 6, 2026, 5:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad798b0f1c81908174b312878e559b |
completed | March 8, 2026, 1:28 p.m. |
Created at: March 4, 2026, 7:29 p.m.