Triple

T7037432
Position Surface form Disambiguated ID Type / Status
Subject Matthew Gregory E163417 entity
Predicate notableWork P4 FINISHED
Object Mad Cows E119027 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: Mad Cows | Statement: [Matthew Gregory, notableWork, Mad Cows]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mad Cows
Context triple: [Matthew Gregory, notableWork, Mad Cows]
  • A. Mad Cows chosen
    Mad Cows is a 1999 British comedy film about a chaotic series of misadventures involving a young mother entangled in crime and bureaucracy.
  • B. Mad Cowgirl
    Mad Cowgirl is a 2006 surreal, low-budget independent horror-thriller film known for its bizarre narrative and cult appeal.
  • C. Concrete Cows
    Concrete Cows is a famous outdoor sculpture in Milton Keynes consisting of life-sized cow figures made from concrete and fiberglass, often seen as an iconic symbol of the town.
  • D. The Cow
    The Cow is the English title of Surah Al-Baqarah, the Quran’s longest chapter, which covers core themes of faith, law, guidance, and the relationship between God and humanity.
  • E. The Cow
    The Cow is a landmark 1969 Iranian drama film directed by Dariush Mehrjui that is widely credited with helping launch the Iranian New Wave.
  • 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_69c6885e7c1c8190be32a8f79ab4e0cf completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e221a7988190b6b69782a275abb7 completed March 27, 2026, 8:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c775a6e1a08190af7d121cb854118e completed March 28, 2026, 6:31 a.m.
Created at: March 27, 2026, 2:36 p.m.