Triple

T731880
Position Surface form Disambiguated ID Type / Status
Subject Coventry E14847 entity
Predicate twinTown P1072 FINISHED
Object Parkes E78089 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: Parkes | Statement: [Coventry, twinTown, Parkes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parkes
Context triple: [Coventry, twinTown, Parkes]
  • A. Parkes chosen
    Parkes is a regional town in central New South Wales, Australia, best known for its nearby radio telescope and annual Elvis Presley Festival.
  • B. Walcha
    Walcha is a rural town in New South Wales, Australia, known for its pastoral farming, cool climate, and location on the Northern Tablelands near the Great Dividing Range.
  • C. Heathcote
    Heathcote is an unincorporated community located within South Brunswick Township in Middlesex County, New Jersey.
  • D. Kingscliff
    Kingscliff is a coastal town in northeastern New South Wales, Australia, known for its beaches, surf breaks, and relaxed holiday atmosphere.
  • E. Yass
    Yass is a historic town in New South Wales, Australia, known as a regional service centre in the Southern Tablelands.
  • 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_69a4934d9930819099eed80096b0597d completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a5d5a6b48190a2c81bfc3c6faa25 completed March 1, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69a65e3df8e48190905f89acbf7f3667 completed March 3, 2026, 4:06 a.m.
Created at: March 1, 2026, 7:37 p.m.