Triple

T13854391
Position Surface form Disambiguated ID Type / Status
Subject Narc E333025 entity
Predicate castMember P1668 FINISHED
Object Anne Openshaw E1127390 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: Anne Openshaw | Statement: [Narc, castMember, Anne Openshaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anne Openshaw
Context triple: [Narc, castMember, Anne Openshaw]
  • A. Anne Openshaw chosen
    Anne Openshaw is a Canadian actress best known for her role on the teen comedy series "Breaker High."
  • B. Elizabeth Shewell
    Elizabeth Shewell was the wife of Anglo-American painter Benjamin West and a member of a prominent Philadelphia Quaker family in the 18th century.
  • C. Mary Shewell
    Mary Shewell was the mother of English critic, essayist, and poet Leigh Hunt, a key figure in the Romantic literary circle.
  • D. Anne Heywood
    Anne Heywood is a British actress known for her film and television roles from the 1950s through the 1970s, often portraying strong, complex female characters.
  • E. Carol Wetherly
    Carol Wetherly is the protagonist of the 1983 post-apocalyptic drama film "Testament," a suburban mother struggling to protect her family after a nuclear attack.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02db9c9c81909bb2d2fbfb7394b1 completed April 14, 2026, 9:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff1a5a733c819090a6710ab990c38d completed May 9, 2026, 11:28 a.m.
Created at: April 9, 2026, 10:14 p.m.