Triple

T18348186
Position Surface form Disambiguated ID Type / Status
Subject Graham Bartram E439596 entity
Predicate memberOf P10 FINISHED
Object Flag Institute 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: Flag Institute | Statement: [Graham Bartram, memberOf, Flag Institute]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Flag Institute
Context triple: [Graham Bartram, memberOf, Flag Institute]
  • A. Flag Institute chosen
    The Flag Institute is the United Kingdom’s principal vexillological and heraldic organization, known for researching, advising on, and maintaining records of British flags.
  • B. PDP Research Group
    PDP Research Group is a collective of cognitive scientists and researchers known for pioneering work on parallel distributed processing and connectionist models of cognition.
  • C. Gallup
    Gallup is a small city in northwestern New Mexico known as a historic stop along Route 66 and a cultural center for Native American art and trading.
  • D. Gallup
    Gallup is a global analytics and advisory company best known for its public opinion polls and research on politics, economics, and well-being.
  • E. Pew Research Center
    Pew Research Center is a nonpartisan American think tank and research organization known for its data-driven studies on social issues, public opinion, demographics, and religion worldwide.
  • 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_69d8b9175fec8190af865699b4e64d8c completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e514f594f88190a683e6224e091593 completed April 19, 2026, 5:46 p.m.
Created at: April 10, 2026, 10:37 a.m.