Triple

T30569164
Position Surface form Disambiguated ID Type / Status
Subject Grace Harding E778073 entity
Predicate marriageOrderWithBorisKarloff P182844 FINISHED
Object first wife of Boris Karloff 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: first wife of Boris Karloff | Statement: [Grace Harding, marriageOrderWithBorisKarloff, first wife of Boris Karloff]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: marriageOrderWithBorisKarloff
Context triple: [Grace Harding, marriageOrderWithBorisKarloff, first wife of Boris Karloff]
  • A. marriageOrderWithBelaLugosi
    Indicates the chronological order in which an entity entered into marriage with Bela Lugosi.
  • B. marriageOrderToBelaLugosi
    Indicates the sequence or ranking of a person’s marriage in relation to their marriage to Bela Lugosi.
  • C. marriageOrderWithClaudeRains
    Indicates the sequence or order in which an entity entered into marriage with Claude Rains relative to his other spouses.
  • D. marriageOrderRelativeToOrsonWelles
    Indicates the position or sequence of a person’s marriage relative to Orson Welles’s own marriages (e.g., earlier, later, or same order).
  • E. marriageOrderWithBillyBobThornton
    Indicates the chronological position in which an entity was married to Billy Bob Thornton relative to his other spouses.
  • 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_69f2249f8c148190ae7eb3912cde112a completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f794f24e588190965e39b77534d53f completed May 3, 2026, 6:33 p.m.
PD Predicate disambiguation batch_69f791033d288190b118029fe412b9c9 completed May 3, 2026, 6:16 p.m.
PDg Predicate description generation batch_69f791cad5e08190a8a04ca283dbecaa completed May 3, 2026, 6:19 p.m.
Created at: April 29, 2026, 8:21 p.m.