Triple

T13776361
Position Surface form Disambiguated ID Type / Status
Subject Diane Chambers E331016 entity
Predicate relationshipTypeWithSamMalone P110908 FINISHED
Object on-again off-again romance 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-again off-again romance | Statement: [Diane Chambers, relationshipTypeWithSamMalone, on-again off-again romance]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithSamMalone
Context triple: [Diane Chambers, relationshipTypeWithSamMalone, on-again off-again romance]
  • A. relationshipToSamBaldwin
    Indicates the specific type of relationship or connection an entity has to Sam Baldwin.
  • B. relationshipToSamCarmichael
    Indicates the specific type of personal or social relationship an entity has with Sam Carmichael.
  • C. relationshipStatusWithMichael
    Indicates the type or state of the relationship that an entity currently has with Michael.
  • D. relationshipTypeWith Jake LaMotta
    Indicates the specific nature or category of relationship that an entity has with Jake LaMotta.
  • E. relationshipToEvanHansen
    Indicates the type or nature of a person's relationship or connection to Evan Hansen.
  • F. None of above. chosen

Provenance (4 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_69d81c583b0081909e408a17db517a21 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0238bdbc8190a946e6e5431632a5 completed April 14, 2026, 9 a.m.
PD Predicate disambiguation batch_69dbbe97846c819093b00ea117b64e0d completed April 12, 2026, 3:47 p.m.
PDg Predicate description generation batch_69dbc59db0148190bcaf9646403ca64f completed April 12, 2026, 4:17 p.m.
Created at: April 9, 2026, 10:10 p.m.