Triple

T20063491
Position Surface form Disambiguated ID Type / Status
Subject Essie Davis E499545 entity
Predicate notableWork P4 FINISHED
Object Cloudstreet 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: Cloudstreet | Statement: [Essie Davis, notableWork, Cloudstreet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cloudstreet
Context triple: [Essie Davis, notableWork, Cloudstreet]
  • A. Cloudstreet chosen
    Cloudstreet is a celebrated Australian television miniseries adaptation of Tim Winton’s novel, depicting the intertwined lives of two working-class families sharing a large house in mid-20th-century Perth.
  • B. City of Swan
    The City of Swan is a local government area in the northeastern metropolitan region of Perth, Western Australia, encompassing a mix of urban, rural, and historic townsites.
  • C. Eureka Street
    Eureka Street is a residential street in San Francisco’s Eureka Valley neighborhood, known for its steep grades and classic city views.
  • D. Eureka Street
    Eureka Street is a British television drama series known for its gritty portrayal of life, politics, and sectarian tensions in late-1990s Belfast.
  • E. Tirra Lirra
    Tirra Lirra is a children's book by Laura E. Richards, best known for its whimsical, lyrical storytelling.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66377b6b48190a0a37279f285123e completed April 20, 2026, 5:33 p.m.
Created at: April 11, 2026, 3:39 p.m.