Triple

T30932933
Position Surface form Disambiguated ID Type / Status
Subject Jan Levinson E788043 entity
Predicate relationshipStatusWithMichaelScott P93770 FINISHED
Object on-and-off romantic relationship LITERAL 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: on-and-off romantic relationship | Statement: [Jan Levinson, relationshipStatusWithMichaelScott, on-and-off romantic relationship]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relationshipStatusWithMichaelScott
Context triple: [Jan Levinson, relationshipStatusWithMichaelScott, on-and-off romantic relationship]
  • A. relationshipStatusWithMichael chosen
    Indicates the type or state of the relationship that an entity currently has with Michael.
  • B. relationshipToPamBeesly
    Indicates the specific type of personal or social relationship an entity has with Pam Beesly.
  • C. relationshipToMike
    Indicates the specific type of personal, social, or familial relationship that an entity has with Mike.
  • D. relationshipToMichelle
    Indicates the specific type of relationship or connection that an entity has to Michelle.
  • E. relationshipStatusWithSam
    Indicates the type or state of the relationship that an entity currently has with Sam.
  • F. None of above.

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_69f224c0b7fc819090cb89df60d23653 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_6a037c876524819098545e6037d3107d completed May 12, 2026, 7:16 p.m.
PD Predicate disambiguation batch_6a0379e2fac0819089b522db3260028c completed May 12, 2026, 7:05 p.m.
Created at: April 29, 2026, 8:52 p.m.