Triple

T22867013
Position Surface form Disambiguated ID Type / Status
Subject Francis Greenway E567081 entity
Predicate familyName P18 FINISHED
Object Greenway 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: Greenway | Statement: [Francis Greenway, familyName, Greenway]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Greenway
Context triple: [Francis Greenway, familyName, Greenway]
  • A. Greenway
    Greenway is a suburb in the Canberra region of the Australian Capital Territory, known for its proximity to Lake Tuggeranong and local commercial and residential areas.
  • B. Greenway chosen
    Greenway is an Australian federal electoral division in western Sydney, New South Wales.
  • C. Greenlane
    Greenlane is a residential and commercial suburb of Auckland, New Zealand, known for its proximity to Cornwall Park and the ASB Showgrounds.
  • D. The Wood Way
    The Wood Way is an art installation by conceptual artist Liam Gillick that reflects his interest in architecture, social systems, and the structures that shape contemporary life.
  • E. Cardinal Greenway
    Cardinal Greenway is a long-distance recreational rail-trail in east-central Indiana popular for walking, running, and cycling.
  • 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_69e24589083081908d5694c4fdc80086 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17f0210b481908e0e6c4f95ba5a3b completed April 29, 2026, 3:46 a.m.
Created at: April 17, 2026, 3:38 p.m.