Triple

T19035815
Position Surface form Disambiguated ID Type / Status
Subject Madeline Martha Mackenzie E465867 entity
Predicate previousMaritalStatus P20884 FINISHED
Object divorced from Nathan Carlson 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: divorced from Nathan Carlson | Statement: [Madeline Martha Mackenzie, previousMaritalStatus, divorced from Nathan Carlson]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: previousMaritalStatus
Context triple: [Madeline Martha Mackenzie, previousMaritalStatus, divorced from Nathan Carlson]
  • A. marital status chosen
    Indicates the legal or social state of a person’s marriage-related relationship, such as being single, married, divorced, or widowed.
  • B. marriedBefore
    Indicates that one entity entered into a marriage at an earlier time than the other entity.
  • C. characterMaritalHistory
    Indicates a relationship that records the sequence of a character’s past and present marital relationships, including spouses and relevant time periods.
  • D. spouseStatusAtMarriage
    Indicates the marital status each partner held at the time their marriage to one another was formed.
  • E. hasMaritalStatusAtEnd
    Indicates that an entity possesses a specific marital status at the end of a given period, event, or reference time.
  • 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d7438f748190912c28912e6b97a6 completed April 20, 2026, 7:35 a.m.
PD Predicate disambiguation batch_69e4a3001e388190aa6057266514e75a completed April 19, 2026, 9:40 a.m.
Created at: April 10, 2026, 12:02 p.m.