Triple

T22709282
Position Surface form Disambiguated ID Type / Status
Subject XY Chelsea E561550 entity
Predicate mainSubject P3 FINISHED
Object Chelsea Manning 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: Chelsea Manning | Statement: [XY Chelsea, mainSubject, Chelsea Manning]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chelsea Manning
Context triple: [XY Chelsea, mainSubject, Chelsea Manning]
  • A. Chelsea Manning chosen
    Chelsea Manning is a former U.S. Army intelligence analyst and whistleblower who leaked classified documents to WikiLeaks, sparking global debates on government transparency, surveillance, and war.
  • B. Lindsay Mills Snowden
    Lindsay Mills Snowden is an American acrobat and blogger best known as the longtime partner of NSA whistleblower Edward Snowden.
  • C. Juliet Snowden
    Juliet Snowden is an American screenwriter known for co-writing supernatural horror films such as "Ouija" and "The Possession."
  • D. Blaine Manning
    Blaine Manning is a former Canadian professional lacrosse forward best known as a star player and multiple-time NLL champion with the Toronto Rock.
  • E. Edward Snowden
    Edward Snowden is a former National Security Agency contractor who became internationally known in 2013 for leaking classified documents revealing global mass surveillance programs.
  • 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_69e2454f1348819088d83f420925a5c1 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178d1e24881909ebd4531c0daef7f completed April 29, 2026, 3:19 a.m.
Created at: April 17, 2026, 3:17 p.m.