Triple

T27090632
Position Surface form Disambiguated ID Type / Status
Subject Lilith Sternin E686156 entity
Predicate relationshipTypeWithFrasierCrane P199499 FINISHED
Object married then divorced 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: married then divorced | Statement: [Lilith Sternin, relationshipTypeWithFrasierCrane, married then divorced]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithFrasierCrane
Context triple: [Lilith Sternin, relationshipTypeWithFrasierCrane, married then divorced]
  • A. hasRelationshipTypeWith Tai Frasier
    Indicates that there exists a specific type of relationship between an entity and Tai Frasier.
  • B. hasRelationshipTypeWith Fran Fine
    Indicates that an entity is connected to Fran Fine by a specific, categorized type of relationship (e.g., familial, professional, romantic, or social).
  • C. relationshipTypeWithFredGraham
    Indicates the specific nature or category of relationship that an entity has with Fred Graham.
  • D. hasRelationshipTypeWith Frank Drebin
    Indicates that there exists a specific type of relationship between an entity and Frank Drebin.
  • E. relationshipTypeWith Francesca Johnson
    Indicates the specific nature or category of the relationship that an entity has with Francesca Johnson.
  • 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_69ef148940ec819097b5c20fbfbf7c81 completed April 27, 2026, 7:47 a.m.
NER Named-entity recognition batch_69ff3fb2318c81908a46c2f513608935 completed May 9, 2026, 2:07 p.m.
PD Predicate disambiguation batch_69ff3e96dcc48190819f6204680d84aa completed May 9, 2026, 2:03 p.m.
PDg Predicate description generation batch_69ff3fb151008190bf8a90f9f1c5f0c8 completed May 9, 2026, 2:07 p.m.
Created at: April 27, 2026, 8:40 a.m.