Triple

T20871267
Position Surface form Disambiguated ID Type / Status
Subject Harry Connick Sr. E513897 entity
Predicate relative P37 FINISHED
Object Harry Connick Jr. E123790 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: Harry Connick Jr. | Statement: [Harry Connick Sr., relative, Harry Connick Jr.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Connick Jr.
Context triple: [Harry Connick Sr., relative, Harry Connick Jr.]
  • A. Harry Connick Jr. chosen
    Harry Connick Jr. is an American singer, pianist, composer, and actor known for his jazz and big band recordings as well as his work in film and television.
  • B. Harry Connick Sr.
    Harry Connick Sr. is an American lawyer and politician best known for serving as the long-time District Attorney of Orleans Parish in New Orleans.
  • C. Dan Riccio
    Dan Riccio is a senior Apple executive and longtime hardware engineering leader known for overseeing the development of many of the company’s major products.
  • D. Richard Cole
    Richard Cole is a fictional character known primarily as the husband of Samantha Cole within their narrative universe.
  • E. Mark Murphy
    Mark Murphy is an American sports executive and former NFL safety who serves as the president and CEO of the Green Bay Packers.
  • 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_69e0b4f675cc8190b4e745225b62eb66 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c4649cf88190b3ad946576aa46aa completed April 21, 2026, 12:27 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09c8e823608190b996eaeb48838aed completed May 17, 2026, 1:55 p.m.
Created at: April 16, 2026, 12:45 p.m.