Triple

T9647896
Position Surface form Disambiguated ID Type / Status
Subject Alison Owen E233252 entity
Predicate notableWork P4 FINISHED
Object Small Island E199129 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: Small Island | Statement: [Alison Owen, notableWork, Small Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Small Island
Context triple: [Alison Owen, notableWork, Small Island]
  • A. Small Island chosen
    "Small Island" is a British television drama adaptation of Andrea Levy's novel about Jamaican immigrants and racial tensions in post-World War II Britain, in which David Oyelowo plays a leading role.
  • B. Sugar Island
    Sugar Island is a small island located in Lake Erie, forming part of the Lake Erie Islands archipelago.
  • C. Sugar Island
    Sugar Island is an island located within Rice Lake in Ontario, Canada, known for its natural scenery and recreational use.
  • D. Our Precious Isles
    Our Precious Isles is an episode of the British nature documentary series "Wild Isles" that focuses on the unique wildlife and natural landscapes of the UK’s islands.
  • E. The Island
    The Island is a 2005 science fiction thriller film directed by Michael Bay that explores themes of human cloning, identity, and corporate ethics.
  • 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_69ca848b31648190b57aa55da20285be completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9b826ff08190a972bdef84405f08 completed April 1, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1825dc8e08190bfc3475cd2e694ba completed April 4, 2026, 9:27 p.m.
Created at: March 30, 2026, 8:13 p.m.