Triple

T16793120
Position Surface form Disambiguated ID Type / Status
Subject John Whitesell E408161 entity
Predicate notableWork P4 FINISHED
Object Suddenly Susan E331553 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: Suddenly Susan | Statement: [John Whitesell, notableWork, Suddenly Susan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Suddenly Susan
Context triple: [John Whitesell, notableWork, Suddenly Susan]
  • A. Suddenly Susan chosen
    Suddenly Susan is an American sitcom that aired in the late 1990s, starring Brooke Shields as a single woman restarting her life and career at a San Francisco magazine.
  • B. Long Susan
    Long Susan is a central character in the British television drama "Ripper Street," known as a brothel madam navigating the dangers and politics of Victorian London's Whitechapel.
  • C. When Susannah Cries
    "When Susannah Cries" is a 1997 pop ballad by Norwegian singer-songwriter Espen Lind that became his breakthrough international hit.
  • D. Little Suzy
    Little Suzy is a precocious, talkative young girl who frequently appears as a comedic side character in the animated television series "Johnny Bravo."
  • E. Little Suzie
    Little Suzie is a character or component within the fictional setting of Wanderland, contributing to its imaginative narrative world.
  • 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_69d88393905081908d00a86b99996ac8 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2a7817c8190a53d0cfb5ef66a71 completed April 18, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00ab0e1e9c8190bb2ef0825b25f6e5 completed May 10, 2026, 3:58 p.m.
Created at: April 10, 2026, 5:22 a.m.