Triple

T1980529
Position Surface form Disambiguated ID Type / Status
Subject Annabella E43014 entity
Predicate child P120 FINISHED
Object Anne Power E215683 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: Anne Power | Statement: [Annabella, child, Anne Power]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anne Power
Context triple: [Annabella, child, Anne Power]
  • A. Anne Power chosen
    Anne Power is a British social policy expert and academic known for her work on urban housing, regeneration, and social exclusion.
  • B. Mary Power
    Mary Power is a personal name shared by multiple individuals, including figures in fields such as academia, politics, and the arts.
  • C. Sarah Eaves
    Sarah Eaves was the partner and later wife of the renowned English printer and typographer John Baskerville, closely involved in his household and business affairs.
  • D. Rachel Hall
    Rachel Hall was a young settler girl taken captive during the 1862 Indian Creek massacre in Illinois, whose abduction and later ransom became a noted episode in American frontier history.
  • E. Alanna Heiss
    Alanna Heiss is an American curator and arts administrator best known for pioneering alternative art spaces and founding the influential contemporary art institution MoMA PS1 in New York City.
  • 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_69a88713ddc88190a969715658ebe7a8 completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb7c87bc081908ed179d1ca94fa3b completed March 7, 2026, 5:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae032bc30c8190a136a634580571d9 completed March 8, 2026, 11:15 p.m.
Created at: March 4, 2026, 7:37 p.m.