Triple

T7102163
Position Surface form Disambiguated ID Type / Status
Subject Super Bowl XI E165483 entity
Predicate referee P268 FINISHED
Object Ben Dreith E210895 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: Ben Dreith | Statement: [Super Bowl XI, referee, Ben Dreith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ben Dreith
Context triple: [Super Bowl XI, referee, Ben Dreith]
  • A. Ben Dreith chosen
    Ben Dreith is a former American football official best known for his long career as an NFL referee, including working high-profile games such as Super Bowl XV.
  • B. Paul Devorski
    Paul Devorski is a retired Canadian National Hockey League referee known for officiating numerous high-profile games over his long career.
  • C. Eric Eldred
    Eric Eldred is an American digital rights activist and publisher known for his work promoting free access to literature and for co-founding the Creative Commons movement.
  • D. Carl Piper
    Carl Piper was a prominent Swedish statesman and close adviser to King Charles XII during the Great Northern War.
  • E. Bryan Woodman
    Bryan Woodman is a young, ambitious energy analyst whose personal tragedy and moral awakening drive one of the central storylines in the geopolitical drama film "Syriana."
  • 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_69c6887fcddc8190a5d58908f6dee590 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e588aee08190bfb3d96135c0a322 completed March 27, 2026, 8:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79ca9b58c8190a91023de6811b21a completed March 28, 2026, 9:17 a.m.
Created at: March 27, 2026, 2:42 p.m.