Triple

T16164096
Position Surface form Disambiguated ID Type / Status
Subject John Irvin E392254 entity
Predicate notableWork P4 FINISHED
Object Shiner E501587 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: Shiner | Statement: [John Irvin, notableWork, Shiner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shiner
Context triple: [John Irvin, notableWork, Shiner]
  • A. Shiner chosen
    Shiner is a film scored by Australian composer Paul Grabowsky, noted for its atmospheric and jazz-influenced soundtrack.
  • B. Blanton
    Blanton is a surname most notably associated with Ray Blanton, an American politician who served as governor of Tennessee in the 1970s.
  • C. Seltz
    Seltz is the principal city and administrative center of the Imperial City of Seltz.
  • D. Sauzon
    Sauzon is a picturesque coastal village and harbor town on Belle-Île-en-Mer in Brittany, France, known for its colorful waterfront and maritime charm.
  • E. Widney
    Widney is a surname most notably associated with Robert Maclay Widney, a prominent 19th-century American judge and one of the founders of the University of Southern California.
  • 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_69d87f1d32208190942e4e499a80c18c completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21e622ae481909f3cf25b38886d3a completed April 17, 2026, 11:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7b69adc8190ba90d68acaaca509 completed May 10, 2026, 3:12 a.m.
Created at: April 10, 2026, 5:02 a.m.