Triple

T4567745
Position Surface form Disambiguated ID Type / Status
Subject The Boston Strangler E121949 entity
Predicate starred P5563 FINISHED
Object Sally Kellerman E243080 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: Sally Kellerman | Statement: [The Boston Strangler, starred, Sally Kellerman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sally Kellerman
Context triple: [The Boston Strangler, starred, Sally Kellerman]
  • A. Sally Kellerman chosen
    Sally Kellerman was an American actress and singer best known for her Oscar-nominated role as Major Margaret "Hot Lips" Houlihan in the film MASH.
  • B. Ellen Casey
    Ellen Casey is the daughter of the late Pennsylvania governor and U.S. senator Robert P. Casey and a member of the prominent Casey political family.
  • C. Carol Seaver
    Carol Seaver is the intelligent, ambitious, and sometimes neurotic teenage daughter in the family sitcom "Growing Pains."
  • D. Susan Patterson
    Susan Patterson is an author and the wife and frequent collaborator of bestselling novelist James Patterson.
  • E. Mary Higgins Clark
    Mary Higgins Clark was a bestselling American author renowned for her suspenseful mystery and thriller novels, often featuring strong female protagonists.
  • 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_69bd463f156881908a99aca69c5721ac completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd589faccc8190ac0354644099810d 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, 1:09 p.m.