Triple

T20265519
Position Surface form Disambiguated ID Type / Status
Subject Ed Hochuli E498956 entity
Predicate nickname P55 FINISHED
Object Ed Hoch NE NERFINISHED

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: Ed Hoch | Statement: [Ed Hochuli, nickname, Ed Hoch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ed Hoch
Context triple: [Ed Hochuli, nickname, Ed Hoch]
  • A. Ed Hoch chosen
    Ed Hoch is a retired American NFL referee renowned for his muscular physique, detailed penalty explanations, and long tenure officiating high-profile games.
  • B. Fred Schuler
    Fred Schuler is a cinematographer best known for his work on films such as the 1980 comedy "Stir Crazy."
  • C. Roger Horchow
    Roger Horchow was an American catalog entrepreneur and Broadway producer known for founding the Horchow Collection and winning a Tony Award for his work in theater.
  • D. Joseph Hoch
    Joseph Hoch was a German lawyer and philanthropist best known for endowing the music school in Frankfurt that became the Hoch Conservatory.
  • E. Ken Hirsch
    Ken Hirsch is an American songwriter and composer known for co-writing numerous pop and R&B hits, including collaborations with prominent lyricists like Doc Pomus.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da6275fa6c8190952924930adee150 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e674cf3d648190a0b0a7795045228a completed April 20, 2026, 6:47 p.m.
Created at: April 11, 2026, 11:41 p.m.