Triple

T11338125
Position Surface form Disambiguated ID Type / Status
Subject Matthew Shear E268523 entity
Predicate participatedIn P149 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: [Matthew Shear, participatedIn, Dead Pigs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dead Pigs
Context triple: [Matthew Shear, participatedIn, 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. 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.
  • C. 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.
  • D. One Pig
    One Pig is an experimental concept album by Matthew Herbert that uses sounds recorded throughout the life cycle of a single pig to explore themes of consumption, ethics, and industrial food production.
  • E. Pigpile
    Pigpile is a live album by the American noise rock band Big Black, capturing one of their final performances with raw, abrasive intensity.
  • 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_69d6aacb1f0881908c84a349fd1be047 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea008b5081908e6c6c6fc29ef936 completed April 9, 2026, 6:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69e55645d8bc8190b338c05ee382d5fc completed April 19, 2026, 10:25 p.m.
Created at: April 8, 2026, 9:33 p.m.