Triple
T16105781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cathy Yan |
E390734
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Dead Pigs |
E919865
|
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: Dead Pigs | Statement: [Cathy Yan, directed, Dead Pigs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dead Pigs Context triple: [Cathy Yan, directed, Dead Pigs]
-
A.
Dead Pigs
chosen
Dead Pigs is a 2018 Chinese-American dark comedy film directed by Cathy Yan that interweaves the lives of several characters in rapidly modernizing Shanghai.
-
B.
All Pigs Must Die
All Pigs Must Die is an American hardcore punk/metal band known for its aggressive sound and featuring members of prominent extreme music groups.
-
C.
Pig Earth
Pig Earth is a collection of interlinked stories and essays by John Berger that portrays the lives, struggles, and culture of French peasant farmers.
-
D.
Looking Good Dead
Looking Good Dead is a crime thriller novel by British author Peter James, featuring Detective Superintendent Roy Grace investigating a brutal murder linked to a sinister online broadcast.
-
E.
Dead Meat
Dead Meat is a segment or component of the series "The Science of Things," likely focusing on scientific or educational content related to meat, decay, or biological processes.
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1ff6d81d081909e1315f4dbfd7369 |
completed | April 17, 2026, 9:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff2a16acc8190be9ed181c7a44def |
completed | May 10, 2026, 2:51 a.m. |
Created at: April 10, 2026, 5 a.m.