Triple

T4852905
Position Surface form Disambiguated ID Type / Status
Subject Boaz E108456 entity
Predicate marriesIn P35908 FINISHED
Object Bethlehem E8382 NE FINISHED

How this triple was built (3 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: Bethlehem | Statement: [Boaz, marriesIn, Bethlehem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bethlehem
Context triple: [Boaz, marriesIn, Bethlehem]
  • A. Bethlehem chosen
    Bethlehem is an ancient town in the West Bank historically revered as the birthplace of Jesus and a major center of Christian pilgrimage.
  • B. Bethlehem
    Bethlehem is a small rural town in western Connecticut known for its historic charm and traditional New England character.
  • C. Bethlehem
    Bethlehem is a suburban town in Albany County, New York, known for its residential communities, schools, and proximity to the city of Albany.
  • D. Beit She'an
    Beit She'an is an ancient city in northeastern Israel known for its extensive archaeological remains, including a well-preserved Roman-Byzantine ruins complex.
  • E. Hebron
    Hebron is a small New England town in central Connecticut known for its rural character, historic charm, and annual agricultural fair.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: marriesIn
Context triple: [Boaz, marriesIn, Bethlehem]
  • A. marries
    Indicates that one entity enters into a legally or socially recognized marital union with another entity.
  • B. marriedIn chosen
    Indicates that two entities entered into a marital relationship at a specific place or within a particular jurisdiction.
  • C. marriedInto
    Indicates that one entity became connected to another’s family or group through marriage, rather than by birth or prior membership.
  • D. hasMarriage
    Indicates a marital relationship exists between the two entities, specifying that they are or were legally married to each other.
  • E. marriedAfter
    Indicates that one marriage occurred later in time than another specified marriage.
  • F. None of above.

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_69bd440a89548190a5f14ba6da6b97dc completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6ddd17d881909f7731ff2b460e83 completed March 20, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69be77907130819084dc6a5eaff42a27 completed March 21, 2026, 10:48 a.m.
PD Predicate disambiguation batch_69bd6c2557388190a2d15571bacd24f3 completed March 20, 2026, 3:47 p.m.
Created at: March 20, 2026, 1:26 p.m.