Triple

T4569278
Position Surface form Disambiguated ID Type / Status
Subject Sullivan E122989 entity
Predicate hasNotableBearer P458 FINISHED
Object Ed Sullivan E426071 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: Ed Sullivan | Statement: [Sullivan, hasNotableBearer, Ed Sullivan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ed Sullivan
Context triple: [Sullivan, hasNotableBearer, Ed Sullivan]
  • A. Ed Sullivan chosen
    Ed Sullivan was a prominent American television host and entertainment columnist best known for creating and hosting the long-running variety program "The Ed Sullivan Show."
  • B. Garry Moore
    Garry Moore was an American television personality and comedian best known for hosting popular mid-20th-century variety and game shows.
  • C. Lawrence Welk
    Lawrence Welk was an American bandleader and television host best known for his long-running musical variety program "The Lawrence Welk Show," featuring easy-listening "champagne music."
  • D. Mel Allen
    Mel Allen was a legendary American sportscaster best known as the longtime voice of the New York Yankees and one of baseball’s most iconic broadcasters.
  • E. Jack Paar
    Jack Paar was an influential American television host and comedian best known for transforming late-night TV during his tenure on The Tonight Show in the late 1950s and early 1960s.
  • 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_69bd46466c7081909d07f36be2d08804 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd58a0dfbc81909b5023f0c29addaf completed March 20, 2026, 2:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdd3bf54448190a7e65cee1a5c48e3 completed March 20, 2026, 11:09 p.m.
Created at: March 20, 2026, 1:10 p.m.