Triple

T18154534
Position Surface form Disambiguated ID Type / Status
Subject Amasa Stone E434594 entity
Predicate givenName P17 FINISHED
Object Amasa NE NERFINISHED

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: Amasa | Statement: [Amasa Stone, givenName, Amasa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amasa
Context triple: [Amasa Stone, givenName, Amasa]
  • A. Amasa chosen
    Amasa is a biblical military commander mentioned in the Old Testament, notably involved in the power struggles during King David’s reign.
  • B. Jehudi Ashmun
    Jehudi Ashmun was an American religious leader and colonization advocate best known for his role in founding and governing the early colony of Liberia.
  • C. Elizur
    Elizur is a masculine given name of Hebrew origin, historically borne by several notable figures in early American history.
  • D. Amasa Gilbert
    Amasa Gilbert was an individual significant enough in local history that the village of Gilberts, Illinois, was named in his honor.
  • E. Amos Burton
    Amos Burton is a tough, morally complex mechanic and enforcer aboard the Rocinante in the science fiction series *The Expanse*.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b90aac308190801e2c57d8c5bfe5 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4de3a99c081908e9615072e62b02f completed April 19, 2026, 1:52 p.m.
Created at: April 10, 2026, 10:30 a.m.