Triple

T9170903
Position Surface form Disambiguated ID Type / Status
Subject Mormon E220076 entity
Predicate child P120 FINISHED
Object Moroni E716673 NE 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: Moroni | Statement: [Mormon, child, Moroni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moroni
Context triple: [Mormon, child, Moroni]
  • A. Moroni
    Moroni is the largest city and political, economic, and cultural center of the island nation of Comoros in the Indian Ocean.
  • B. Moroni
    Moroni is the given first name of American silent film actor and comedian Mack Swain.
  • C. Hyrum
    Hyrum is a small city in northern Utah known for its agricultural roots and proximity to outdoor recreation in the Cache Valley.
  • D. Moroni Swain chosen
    Moroni Swain was the birth name of Mack Swain, an American silent film actor and comedian known for his work with Charlie Chaplin and in early Keystone comedies.
  • E. Lehi
    Lehi was a radical Zionist paramilitary organization in Mandatory Palestine known for its militant struggle against British rule and controversial tactics during the 1940s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca83e467108190abcae6a33b3d4dad completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccaae38ee48190bf783477bc37913d completed April 1, 2026, 5:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0549746b0819099c2a591900f9c8c completed April 4, 2026, midnight
Created at: March 30, 2026, 7:22 p.m.