Triple

T10130212
Position Surface form Disambiguated ID Type / Status
Subject Eddie Deezen E226317 entity
Predicate name P16 FINISHED
Object Eddie Deezen E226317 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: Eddie Deezen | Statement: [Eddie Deezen, name, Eddie Deezen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eddie Deezen
Context triple: [Eddie Deezen, name, Eddie Deezen]
  • A. Eddie Deezen chosen
    Eddie Deezen is an American character actor and voice actor known for his distinctive nerdy persona in films like "Grease" and numerous animated productions.
  • B. Eddie Brinkman
    Eddie Brinkman was an American Major League Baseball shortstop known primarily for his strong defensive play during the 1960s and early 1970s.
  • C. Jerry Seeman
    Jerry Seeman was a prominent NFL official who served as a referee in multiple Super Bowls and later became the league’s Director of Officiating.
  • D. Ian Deitchman
    Ian Deitchman is a screenwriter known for his work on film and television projects, including contributing to the animated musical special "Entergalactic."
  • E. John Zaccaro
    John Zaccaro is an American real estate developer best known as the husband of the late U.S. Congresswoman and 1984 vice-presidential nominee Geraldine Ferraro.
  • 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_69ca843057b48190a86730167f5d6b98 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdd33438988190be45878f98695816 completed April 2, 2026, 2:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cc7c50b08190a04aa2f58a6c300a completed April 5, 2026, 8:56 p.m.
Created at: March 30, 2026, 9:05 p.m.