Triple

T4077613
Position Surface form Disambiguated ID Type / Status
Subject John Key E87402 entity
Predicate name P16 FINISHED
Object John Key E87402 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: John Key | Statement: [John Key, name, John Key]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Key
Context triple: [John Key, name, John Key]
  • A. John Key chosen
    John Key is a New Zealand politician and businessman who served as the 38th Prime Minister of New Zealand from 2008 to 2016.
  • B. Tony Abbott
    Tony Abbott is an Australian politician who served as the 28th Prime Minister of Australia from 2013 to 2015 and long-time member of the Liberal Party.
  • C. Malcolm Turnbull
    Malcolm Turnbull is an Australian businessman, lawyer, and politician who served as the 29th Prime Minister of Australia from 2015 to 2018.
  • D. Scott Morrison
    Scott Morrison is an Australian politician who served as the 30th Prime Minister of Australia from 2018 to 2022.
  • E. Andrew Little
    Andrew Little is a New Zealand politician and former leader of the Labour Party who served as Leader of the Opposition before later holding several ministerial roles in government.
  • 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_69aed9435cf48190ad1da737c962d19d completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefc4d348c8190a94724639830aca0 completed March 9, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562bea9b48190bcd1396c0cb19697 completed March 14, 2026, 1:29 p.m.
Created at: March 9, 2026, 3:39 p.m.